[PATCH V2 0/3] hwmon (coretemp): Add support for dynamic tjmax/ttarget

[PATCH V2 0/3] hwmon (coretemp): Add support for dynamic tjmax/ttarget

[Zhang Rui]

Tjmax value retrieved from MSR_IA32_TEMPERATURE_TARGET can be changed at
runtime when the Intel SST-PP (Intel Speed Select Technology - Performance
Profile) level is changed. As a result, the ttarget temperature also changes.

Enhance the coretemp driver to always use updated tjmax when it can be
retrieved from MSR_IA32_TEMPERATURE_TARGET.

When tjmax can not be retrieved from MSR_IA32_TEMPERATURE_TARGET, stick with
previous behavior and always use static value. Plus that ttarget is not
available in this case.

The same dynaimic tjmax enhancement, for driver/thermal drivers can be found
at https://patchwork.kernel.org/project/linux-pm/list/?series=693050

thanks,
rui

---
Changes since V1:
- rearrange the code to avoid forward declaration
- optimize logic to check target temperature support only once
- coding style changes

[PATCH V2 1/3] hwmon (coretemp): rearrange tjmax handing code

[Zhang Rui]

Rearrange the tjmax handling code so that it can be used directly in
the sysfs attribute callbacks without forward declarations.

No functional change in this patch.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 drivers/hwmon/coretemp.c | 156 +++++++++++++++++++--------------------
 1 file changed, 78 insertions(+), 78 deletions(-)

diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index ec35ada68455..50b640bfa504 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -93,84 +93,6 @@ struct platform_data {
 	struct device_attribute name_attr;
 };
 
-/* Keep track of how many zone pointers we allocated in init() */
-static int max_zones __read_mostly;
-/* Array of zone pointers. Serialized by cpu hotplug lock */
-static struct platform_device **zone_devices;
-
-static ssize_t show_label(struct device *dev,
-				struct device_attribute *devattr, char *buf)
-{
-	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
-	struct platform_data *pdata = dev_get_drvdata(dev);
-	struct temp_data *tdata = pdata->core_data[attr->index];
-
-	if (tdata->is_pkg_data)
-		return sprintf(buf, "Package id %u\n", pdata->pkg_id);
-
-	return sprintf(buf, "Core %u\n", tdata->cpu_core_id);
-}
-
-static ssize_t show_crit_alarm(struct device *dev,
-				struct device_attribute *devattr, char *buf)
-{
-	u32 eax, edx;
-	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
-	struct platform_data *pdata = dev_get_drvdata(dev);
-	struct temp_data *tdata = pdata->core_data[attr->index];
-
-	mutex_lock(&tdata->update_lock);
-	rdmsr_on_cpu(tdata->cpu, tdata->status_reg, &eax, &edx);
-	mutex_unlock(&tdata->update_lock);
-
-	return sprintf(buf, "%d\n", (eax >> 5) & 1);
-}
-
-static ssize_t show_tjmax(struct device *dev,
-			struct device_attribute *devattr, char *buf)
-{
-	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
-	struct platform_data *pdata = dev_get_drvdata(dev);
-
-	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->tjmax);
-}
-
-static ssize_t show_ttarget(struct device *dev,
-				struct device_attribute *devattr, char *buf)
-{
-	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
-	struct platform_data *pdata = dev_get_drvdata(dev);
-
-	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->ttarget);
-}
-
-static ssize_t show_temp(struct device *dev,
-			struct device_attribute *devattr, char *buf)
-{
-	u32 eax, edx;
-	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
-	struct platform_data *pdata = dev_get_drvdata(dev);
-	struct temp_data *tdata = pdata->core_data[attr->index];
-
-	mutex_lock(&tdata->update_lock);
-
-	/* Check whether the time interval has elapsed */
-	if (time_after(jiffies, tdata->last_updated + HZ)) {
-		rdmsr_on_cpu(tdata->cpu, tdata->status_reg, &eax, &edx);
-		/*
-		 * Ignore the valid bit. In all observed cases the register
-		 * value is either low or zero if the valid bit is 0.
-		 * Return it instead of reporting an error which doesn't
-		 * really help at all.
-		 */
-		tdata->temp = tdata->tjmax - ((eax >> 16) & 0x7f) * 1000;
-		tdata->last_updated = jiffies;
-	}
-
-	mutex_unlock(&tdata->update_lock);
-	return sprintf(buf, "%d\n", tdata->temp);
-}
-
 struct tjmax_pci {
 	unsigned int device;
 	int tjmax;
@@ -373,6 +295,84 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 	return adjust_tjmax(c, id, dev);
 }
 
+/* Keep track of how many zone pointers we allocated in init() */
+static int max_zones __read_mostly;
+/* Array of zone pointers. Serialized by cpu hotplug lock */
+static struct platform_device **zone_devices;
+
+static ssize_t show_label(struct device *dev,
+				struct device_attribute *devattr, char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct platform_data *pdata = dev_get_drvdata(dev);
+	struct temp_data *tdata = pdata->core_data[attr->index];
+
+	if (tdata->is_pkg_data)
+		return sprintf(buf, "Package id %u\n", pdata->pkg_id);
+
+	return sprintf(buf, "Core %u\n", tdata->cpu_core_id);
+}
+
+static ssize_t show_crit_alarm(struct device *dev,
+				struct device_attribute *devattr, char *buf)
+{
+	u32 eax, edx;
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct platform_data *pdata = dev_get_drvdata(dev);
+	struct temp_data *tdata = pdata->core_data[attr->index];
+
+	mutex_lock(&tdata->update_lock);
+	rdmsr_on_cpu(tdata->cpu, tdata->status_reg, &eax, &edx);
+	mutex_unlock(&tdata->update_lock);
+
+	return sprintf(buf, "%d\n", (eax >> 5) & 1);
+}
+
+static ssize_t show_tjmax(struct device *dev,
+			struct device_attribute *devattr, char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct platform_data *pdata = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->tjmax);
+}
+
+static ssize_t show_ttarget(struct device *dev,
+				struct device_attribute *devattr, char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct platform_data *pdata = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->ttarget);
+}
+
+static ssize_t show_temp(struct device *dev,
+			struct device_attribute *devattr, char *buf)
+{
+	u32 eax, edx;
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct platform_data *pdata = dev_get_drvdata(dev);
+	struct temp_data *tdata = pdata->core_data[attr->index];
+
+	mutex_lock(&tdata->update_lock);
+
+	/* Check whether the time interval has elapsed */
+	if (time_after(jiffies, tdata->last_updated + HZ)) {
+		rdmsr_on_cpu(tdata->cpu, tdata->status_reg, &eax, &edx);
+		/*
+		 * Ignore the valid bit. In all observed cases the register
+		 * value is either low or zero if the valid bit is 0.
+		 * Return it instead of reporting an error which doesn't
+		 * really help at all.
+		 */
+		tdata->temp = tdata->tjmax - ((eax >> 16) & 0x7f) * 1000;
+		tdata->last_updated = jiffies;
+	}
+
+	mutex_unlock(&tdata->update_lock);
+	return sprintf(buf, "%d\n", tdata->temp);
+}
+
 static int create_core_attrs(struct temp_data *tdata, struct device *dev,
 			     int attr_no)
 {
-- 
2.25.1

[PATCH V2 2/3] hwmon (coretemp): Add support for dynamic tjmax

[Zhang Rui]

Tjmax value retrieved from MSR_IA32_TEMPERATURE_TARGET can be changed at
runtime when the Intel SST-PP (Intel Speed Select Technology -
Performance Profile) level is changed.

Improve the code to always use updated tjmax when it can be retrieved
from MSR_IA32_TEMPERATURE_TARGET.

When tjmax can not be retrieved from MSR_IA32_TEMPERATURE_TARGET, still
follow the previous logic and always use a static tjmax value.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 drivers/hwmon/coretemp.c | 46 +++++++++++++++++++++++++++-------------
 1 file changed, 31 insertions(+), 15 deletions(-)

diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index 50b640bfa504..573ac8c5ed42 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -55,6 +55,8 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
 
 /*
  * Per-Core Temperature Data
+ * @tjmax: The static tjmax value when tjmax cannot be retrieved from
+ *		IA32_TEMPERATURE_TARGET MSR.
  * @last_updated: The time when the current temperature value was updated
  *		earlier (in jiffies).
  * @cpu_core_id: The CPU Core from which temperature values should be read
@@ -256,20 +258,25 @@ static bool cpu_has_tjmax(struct cpuinfo_x86 *c)
 	       model != 0x36;
 }
 
-static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
+static int get_tjmax(struct temp_data *tdata, struct device *dev)
 {
+	struct cpuinfo_x86 *c = &cpu_data(tdata->cpu);
 	int err;
 	u32 eax, edx;
 	u32 val;
 
+	/* use static tjmax once it is set */
+	if (tdata->tjmax)
+		return tdata->tjmax;
+
 	/*
 	 * A new feature of current Intel(R) processors, the
 	 * IA32_TEMPERATURE_TARGET contains the TjMax value
 	 */
-	err = rdmsr_safe_on_cpu(id, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
+	err = rdmsr_safe_on_cpu(tdata->cpu, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
 	if (err) {
 		if (cpu_has_tjmax(c))
-			dev_warn(dev, "Unable to read TjMax from CPU %u\n", id);
+			dev_warn(dev, "Unable to read TjMax from CPU %u\n", tdata->cpu);
 	} else {
 		val = (eax >> 16) & 0xff;
 		/*
@@ -285,14 +292,15 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 	if (force_tjmax) {
 		dev_notice(dev, "TjMax forced to %d degrees C by user\n",
 			   force_tjmax);
-		return force_tjmax * 1000;
+		tdata->tjmax = force_tjmax * 1000;
+	} else {
+		/*
+		 * An assumption is made for early CPUs and unreadable MSR.
+		 * NOTE: the calculated value may not be correct.
+		 */
+		tdata->tjmax = adjust_tjmax(c, tdata->cpu, dev);
 	}
-
-	/*
-	 * An assumption is made for early CPUs and unreadable MSR.
-	 * NOTE: the calculated value may not be correct.
-	 */
-	return adjust_tjmax(c, id, dev);
+	return tdata->tjmax;
 }
 
 /* Keep track of how many zone pointers we allocated in init() */
@@ -333,8 +341,14 @@ static ssize_t show_tjmax(struct device *dev,
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct platform_data *pdata = dev_get_drvdata(dev);
+	struct temp_data *tdata = pdata->core_data[attr->index];
+	int tjmax;
+
+	mutex_lock(&tdata->update_lock);
+	tjmax = get_tjmax(tdata, dev);
+	mutex_unlock(&tdata->update_lock);
 
-	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->tjmax);
+	return sprintf(buf, "%d\n", tjmax);
 }
 
 static ssize_t show_ttarget(struct device *dev,
@@ -353,9 +367,11 @@ static ssize_t show_temp(struct device *dev,
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct platform_data *pdata = dev_get_drvdata(dev);
 	struct temp_data *tdata = pdata->core_data[attr->index];
+	int tjmax;
 
 	mutex_lock(&tdata->update_lock);
 
+	tjmax = get_tjmax(tdata, dev);
 	/* Check whether the time interval has elapsed */
 	if (time_after(jiffies, tdata->last_updated + HZ)) {
 		rdmsr_on_cpu(tdata->cpu, tdata->status_reg, &eax, &edx);
@@ -365,7 +381,7 @@ static ssize_t show_temp(struct device *dev,
 		 * Return it instead of reporting an error which doesn't
 		 * really help at all.
 		 */
-		tdata->temp = tdata->tjmax - ((eax >> 16) & 0x7f) * 1000;
+		tdata->temp = tjmax - ((eax >> 16) & 0x7f) * 1000;
 		tdata->last_updated = jiffies;
 	}
 
@@ -450,7 +466,7 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
 	struct platform_data *pdata = platform_get_drvdata(pdev);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	u32 eax, edx;
-	int err, index, attr_no;
+	int err, index, attr_no, tjmax;
 
 	/*
 	 * Find attr number for sysfs:
@@ -485,7 +501,7 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
 		goto exit_free;
 
 	/* We can access status register. Get Critical Temperature */
-	tdata->tjmax = get_tjmax(c, cpu, &pdev->dev);
+	tjmax = get_tjmax(tdata, &pdev->dev);
 
 	/*
 	 * Read the still undocumented bits 8:15 of IA32_TEMPERATURE_TARGET.
@@ -497,7 +513,7 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
 					&eax, &edx);
 		if (!err) {
 			tdata->ttarget
-			  = tdata->tjmax - ((eax >> 8) & 0xff) * 1000;
+			  = tjmax - ((eax >> 8) & 0xff) * 1000;
 			tdata->attr_size++;
 		}
 	}
-- 
2.25.1

[PATCH V2 3/3] hwmon (coretemp): Add support for dynamic ttarget

[Zhang Rui]

Tjmax value retrieved from MSR_IA32_TEMPERATURE_TARGET can be changed at
runtime when the Intel SST-PP (Intel Speed Select Technology -
Performance Profile) level is changed. As a result, the ttarget value
also becomes dyamic.

Improve the code to always get updated ttarget value.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
---
 drivers/hwmon/coretemp.c | 57 +++++++++++++++++++++++++++++-----------
 1 file changed, 41 insertions(+), 16 deletions(-)

diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index 573ac8c5ed42..e537ab0d0422 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -69,7 +69,6 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
  */
 struct temp_data {
 	int temp;
-	int ttarget;
 	int tjmax;
 	unsigned long last_updated;
 	unsigned int cpu;
@@ -303,6 +302,30 @@ static int get_tjmax(struct temp_data *tdata, struct device *dev)
 	return tdata->tjmax;
 }
 
+static int get_ttarget(struct temp_data *tdata, struct device *dev)
+{
+	u32 eax, edx;
+	int tjmax, ttarget_offset, ret;
+
+	/*
+	 * ttarget is valid only if tjmax can be retrieved from
+	 * MSR_IA32_TEMPERATURE_TARGET
+	 */
+	if (tdata->tjmax)
+		return -ENODEV;
+
+	ret = rdmsr_safe_on_cpu(tdata->cpu, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
+	if (ret)
+		return ret;
+
+	tjmax = (eax >> 16) & 0xff;
+
+	/* Read the still undocumented bits 8:15 of IA32_TEMPERATURE_TARGET. */
+	ttarget_offset = (eax >> 8) & 0xff;
+
+	return (tjmax - ttarget_offset) * 1000;
+}
+
 /* Keep track of how many zone pointers we allocated in init() */
 static int max_zones __read_mostly;
 /* Array of zone pointers. Serialized by cpu hotplug lock */
@@ -356,8 +379,16 @@ static ssize_t show_ttarget(struct device *dev,
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct platform_data *pdata = dev_get_drvdata(dev);
+	struct temp_data *tdata = pdata->core_data[attr->index];
+	int ttarget;
 
-	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->ttarget);
+	mutex_lock(&tdata->update_lock);
+	ttarget = get_ttarget(tdata, dev);
+	mutex_unlock(&tdata->update_lock);
+
+	if (ttarget < 0)
+		return ttarget;
+	return sprintf(buf, "%d\n", ttarget);
 }
 
 static ssize_t show_temp(struct device *dev,
@@ -466,7 +497,7 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
 	struct platform_data *pdata = platform_get_drvdata(pdev);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	u32 eax, edx;
-	int err, index, attr_no, tjmax;
+	int err, index, attr_no;
 
 	/*
 	 * Find attr number for sysfs:
@@ -500,23 +531,17 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
 	if (err)
 		goto exit_free;
 
-	/* We can access status register. Get Critical Temperature */
-	tjmax = get_tjmax(tdata, &pdev->dev);
+	/* Make sure tdata->tjmax is a valid indicator for dynamic/static tjmax */
+	get_tjmax(tdata, &pdev->dev);
 
 	/*
-	 * Read the still undocumented bits 8:15 of IA32_TEMPERATURE_TARGET.
-	 * The target temperature is available on older CPUs but not in this
-	 * register. Atoms don't have the register at all.
+	 * The target temperature is available on older CPUs but not in the
+	 * MSR_IA32_TEMPERATURE_TARGET register. Atoms don't have the register
+	 * at all.
 	 */
-	if (c->x86_model > 0xe && c->x86_model != 0x1c) {
-		err = rdmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET,
-					&eax, &edx);
-		if (!err) {
-			tdata->ttarget
-			  = tjmax - ((eax >> 8) & 0xff) * 1000;
+	if (c->x86_model > 0xe && c->x86_model != 0x1c)
+		if (get_ttarget(tdata, &pdev->dev) >= 0)
 			tdata->attr_size++;
-		}
-	}
 
 	pdata->core_data[attr_no] = tdata;
 
-- 
2.25.1

Re: [PATCH V2 1/3] hwmon (coretemp): rearrange tjmax handing code

[Guenter Roeck]

On Sun, Nov 13, 2022 at 11:31:43PM +0800, Zhang Rui wrote:
> Rearrange the tjmax handling code so that it can be used directly in
> the sysfs attribute callbacks without forward declarations.
> 
> No functional change in this patch.
> 
> Signed-off-by: Zhang Rui <rui.zhang@intel.com>

Applied to hwmon-next.

Thanks,
Guenter

> ---
>  drivers/hwmon/coretemp.c | 156 +++++++++++++++++++--------------------
>  1 file changed, 78 insertions(+), 78 deletions(-)
> 
> diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
> index ec35ada68455..50b640bfa504 100644
> --- a/drivers/hwmon/coretemp.c
> +++ b/drivers/hwmon/coretemp.c
> @@ -93,84 +93,6 @@ struct platform_data {
>  	struct device_attribute name_attr;
>  };
>  
> -/* Keep track of how many zone pointers we allocated in init() */
> -static int max_zones __read_mostly;
> -/* Array of zone pointers. Serialized by cpu hotplug lock */
> -static struct platform_device **zone_devices;
> -
> -static ssize_t show_label(struct device *dev,
> -				struct device_attribute *devattr, char *buf)
> -{
> -	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
> -	struct platform_data *pdata = dev_get_drvdata(dev);
> -	struct temp_data *tdata = pdata->core_data[attr->index];
> -
> -	if (tdata->is_pkg_data)
> -		return sprintf(buf, "Package id %u\n", pdata->pkg_id);
> -
> -	return sprintf(buf, "Core %u\n", tdata->cpu_core_id);
> -}
> -
> -static ssize_t show_crit_alarm(struct device *dev,
> -				struct device_attribute *devattr, char *buf)
> -{
> -	u32 eax, edx;
> -	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
> -	struct platform_data *pdata = dev_get_drvdata(dev);
> -	struct temp_data *tdata = pdata->core_data[attr->index];
> -
> -	mutex_lock(&tdata->update_lock);
> -	rdmsr_on_cpu(tdata->cpu, tdata->status_reg, &eax, &edx);
> -	mutex_unlock(&tdata->update_lock);
> -
> -	return sprintf(buf, "%d\n", (eax >> 5) & 1);
> -}
> -
> -static ssize_t show_tjmax(struct device *dev,
> -			struct device_attribute *devattr, char *buf)
> -{
> -	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
> -	struct platform_data *pdata = dev_get_drvdata(dev);
> -
> -	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->tjmax);
> -}
> -
> -static ssize_t show_ttarget(struct device *dev,
> -				struct device_attribute *devattr, char *buf)
> -{
> -	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
> -	struct platform_data *pdata = dev_get_drvdata(dev);
> -
> -	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->ttarget);
> -}
> -
> -static ssize_t show_temp(struct device *dev,
> -			struct device_attribute *devattr, char *buf)
> -{
> -	u32 eax, edx;
> -	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
> -	struct platform_data *pdata = dev_get_drvdata(dev);
> -	struct temp_data *tdata = pdata->core_data[attr->index];
> -
> -	mutex_lock(&tdata->update_lock);
> -
> -	/* Check whether the time interval has elapsed */
> -	if (time_after(jiffies, tdata->last_updated + HZ)) {
> -		rdmsr_on_cpu(tdata->cpu, tdata->status_reg, &eax, &edx);
> -		/*
> -		 * Ignore the valid bit. In all observed cases the register
> -		 * value is either low or zero if the valid bit is 0.
> -		 * Return it instead of reporting an error which doesn't
> -		 * really help at all.
> -		 */
> -		tdata->temp = tdata->tjmax - ((eax >> 16) & 0x7f) * 1000;
> -		tdata->last_updated = jiffies;
> -	}
> -
> -	mutex_unlock(&tdata->update_lock);
> -	return sprintf(buf, "%d\n", tdata->temp);
> -}
> -
>  struct tjmax_pci {
>  	unsigned int device;
>  	int tjmax;
> @@ -373,6 +295,84 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
>  	return adjust_tjmax(c, id, dev);
>  }
>  
> +/* Keep track of how many zone pointers we allocated in init() */
> +static int max_zones __read_mostly;
> +/* Array of zone pointers. Serialized by cpu hotplug lock */
> +static struct platform_device **zone_devices;
> +
> +static ssize_t show_label(struct device *dev,
> +				struct device_attribute *devattr, char *buf)
> +{
> +	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
> +	struct platform_data *pdata = dev_get_drvdata(dev);
> +	struct temp_data *tdata = pdata->core_data[attr->index];
> +
> +	if (tdata->is_pkg_data)
> +		return sprintf(buf, "Package id %u\n", pdata->pkg_id);
> +
> +	return sprintf(buf, "Core %u\n", tdata->cpu_core_id);
> +}
> +
> +static ssize_t show_crit_alarm(struct device *dev,
> +				struct device_attribute *devattr, char *buf)
> +{
> +	u32 eax, edx;
> +	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
> +	struct platform_data *pdata = dev_get_drvdata(dev);
> +	struct temp_data *tdata = pdata->core_data[attr->index];
> +
> +	mutex_lock(&tdata->update_lock);
> +	rdmsr_on_cpu(tdata->cpu, tdata->status_reg, &eax, &edx);
> +	mutex_unlock(&tdata->update_lock);
> +
> +	return sprintf(buf, "%d\n", (eax >> 5) & 1);
> +}
> +
> +static ssize_t show_tjmax(struct device *dev,
> +			struct device_attribute *devattr, char *buf)
> +{
> +	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
> +	struct platform_data *pdata = dev_get_drvdata(dev);
> +
> +	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->tjmax);
> +}
> +
> +static ssize_t show_ttarget(struct device *dev,
> +				struct device_attribute *devattr, char *buf)
> +{
> +	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
> +	struct platform_data *pdata = dev_get_drvdata(dev);
> +
> +	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->ttarget);
> +}
> +
> +static ssize_t show_temp(struct device *dev,
> +			struct device_attribute *devattr, char *buf)
> +{
> +	u32 eax, edx;
> +	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
> +	struct platform_data *pdata = dev_get_drvdata(dev);
> +	struct temp_data *tdata = pdata->core_data[attr->index];
> +
> +	mutex_lock(&tdata->update_lock);
> +
> +	/* Check whether the time interval has elapsed */
> +	if (time_after(jiffies, tdata->last_updated + HZ)) {
> +		rdmsr_on_cpu(tdata->cpu, tdata->status_reg, &eax, &edx);
> +		/*
> +		 * Ignore the valid bit. In all observed cases the register
> +		 * value is either low or zero if the valid bit is 0.
> +		 * Return it instead of reporting an error which doesn't
> +		 * really help at all.
> +		 */
> +		tdata->temp = tdata->tjmax - ((eax >> 16) & 0x7f) * 1000;
> +		tdata->last_updated = jiffies;
> +	}
> +
> +	mutex_unlock(&tdata->update_lock);
> +	return sprintf(buf, "%d\n", tdata->temp);
> +}
> +
>  static int create_core_attrs(struct temp_data *tdata, struct device *dev,
>  			     int attr_no)
>  {

Re: [PATCH V2 2/3] hwmon (coretemp): Add support for dynamic tjmax

[Guenter Roeck]

On Sun, Nov 13, 2022 at 11:31:44PM +0800, Zhang Rui wrote:
> Tjmax value retrieved from MSR_IA32_TEMPERATURE_TARGET can be changed at
> runtime when the Intel SST-PP (Intel Speed Select Technology -
> Performance Profile) level is changed.
> 
> Improve the code to always use updated tjmax when it can be retrieved
> from MSR_IA32_TEMPERATURE_TARGET.
> 
> When tjmax can not be retrieved from MSR_IA32_TEMPERATURE_TARGET, still
> follow the previous logic and always use a static tjmax value.
> 
> Signed-off-by: Zhang Rui <rui.zhang@intel.com>

Applied to hwmon-next.

Thanks,
Guenter

> ---
>  drivers/hwmon/coretemp.c | 46 +++++++++++++++++++++++++++-------------
>  1 file changed, 31 insertions(+), 15 deletions(-)
> 
> diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
> index 50b640bfa504..573ac8c5ed42 100644
> --- a/drivers/hwmon/coretemp.c
> +++ b/drivers/hwmon/coretemp.c
> @@ -55,6 +55,8 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
>  
>  /*
>   * Per-Core Temperature Data
> + * @tjmax: The static tjmax value when tjmax cannot be retrieved from
> + *		IA32_TEMPERATURE_TARGET MSR.
>   * @last_updated: The time when the current temperature value was updated
>   *		earlier (in jiffies).
>   * @cpu_core_id: The CPU Core from which temperature values should be read
> @@ -256,20 +258,25 @@ static bool cpu_has_tjmax(struct cpuinfo_x86 *c)
>  	       model != 0x36;
>  }
>  
> -static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
> +static int get_tjmax(struct temp_data *tdata, struct device *dev)
>  {
> +	struct cpuinfo_x86 *c = &cpu_data(tdata->cpu);
>  	int err;
>  	u32 eax, edx;
>  	u32 val;
>  
> +	/* use static tjmax once it is set */
> +	if (tdata->tjmax)
> +		return tdata->tjmax;
> +
>  	/*
>  	 * A new feature of current Intel(R) processors, the
>  	 * IA32_TEMPERATURE_TARGET contains the TjMax value
>  	 */
> -	err = rdmsr_safe_on_cpu(id, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
> +	err = rdmsr_safe_on_cpu(tdata->cpu, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
>  	if (err) {
>  		if (cpu_has_tjmax(c))
> -			dev_warn(dev, "Unable to read TjMax from CPU %u\n", id);
> +			dev_warn(dev, "Unable to read TjMax from CPU %u\n", tdata->cpu);
>  	} else {
>  		val = (eax >> 16) & 0xff;
>  		/*
> @@ -285,14 +292,15 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
>  	if (force_tjmax) {
>  		dev_notice(dev, "TjMax forced to %d degrees C by user\n",
>  			   force_tjmax);
> -		return force_tjmax * 1000;
> +		tdata->tjmax = force_tjmax * 1000;
> +	} else {
> +		/*
> +		 * An assumption is made for early CPUs and unreadable MSR.
> +		 * NOTE: the calculated value may not be correct.
> +		 */
> +		tdata->tjmax = adjust_tjmax(c, tdata->cpu, dev);
>  	}
> -
> -	/*
> -	 * An assumption is made for early CPUs and unreadable MSR.
> -	 * NOTE: the calculated value may not be correct.
> -	 */
> -	return adjust_tjmax(c, id, dev);
> +	return tdata->tjmax;
>  }
>  
>  /* Keep track of how many zone pointers we allocated in init() */
> @@ -333,8 +341,14 @@ static ssize_t show_tjmax(struct device *dev,
>  {
>  	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
>  	struct platform_data *pdata = dev_get_drvdata(dev);
> +	struct temp_data *tdata = pdata->core_data[attr->index];
> +	int tjmax;
> +
> +	mutex_lock(&tdata->update_lock);
> +	tjmax = get_tjmax(tdata, dev);
> +	mutex_unlock(&tdata->update_lock);
>  
> -	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->tjmax);
> +	return sprintf(buf, "%d\n", tjmax);
>  }
>  
>  static ssize_t show_ttarget(struct device *dev,
> @@ -353,9 +367,11 @@ static ssize_t show_temp(struct device *dev,
>  	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
>  	struct platform_data *pdata = dev_get_drvdata(dev);
>  	struct temp_data *tdata = pdata->core_data[attr->index];
> +	int tjmax;
>  
>  	mutex_lock(&tdata->update_lock);
>  
> +	tjmax = get_tjmax(tdata, dev);
>  	/* Check whether the time interval has elapsed */
>  	if (time_after(jiffies, tdata->last_updated + HZ)) {
>  		rdmsr_on_cpu(tdata->cpu, tdata->status_reg, &eax, &edx);
> @@ -365,7 +381,7 @@ static ssize_t show_temp(struct device *dev,
>  		 * Return it instead of reporting an error which doesn't
>  		 * really help at all.
>  		 */
> -		tdata->temp = tdata->tjmax - ((eax >> 16) & 0x7f) * 1000;
> +		tdata->temp = tjmax - ((eax >> 16) & 0x7f) * 1000;
>  		tdata->last_updated = jiffies;
>  	}
>  
> @@ -450,7 +466,7 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
>  	struct platform_data *pdata = platform_get_drvdata(pdev);
>  	struct cpuinfo_x86 *c = &cpu_data(cpu);
>  	u32 eax, edx;
> -	int err, index, attr_no;
> +	int err, index, attr_no, tjmax;
>  
>  	/*
>  	 * Find attr number for sysfs:
> @@ -485,7 +501,7 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
>  		goto exit_free;
>  
>  	/* We can access status register. Get Critical Temperature */
> -	tdata->tjmax = get_tjmax(c, cpu, &pdev->dev);
> +	tjmax = get_tjmax(tdata, &pdev->dev);
>  
>  	/*
>  	 * Read the still undocumented bits 8:15 of IA32_TEMPERATURE_TARGET.
> @@ -497,7 +513,7 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
>  					&eax, &edx);
>  		if (!err) {
>  			tdata->ttarget
> -			  = tdata->tjmax - ((eax >> 8) & 0xff) * 1000;
> +			  = tjmax - ((eax >> 8) & 0xff) * 1000;
>  			tdata->attr_size++;
>  		}
>  	}

Re: [PATCH V2 3/3] hwmon (coretemp): Add support for dynamic ttarget

[Guenter Roeck]

On Sun, Nov 13, 2022 at 11:31:45PM +0800, Zhang Rui wrote:
> Tjmax value retrieved from MSR_IA32_TEMPERATURE_TARGET can be changed at
> runtime when the Intel SST-PP (Intel Speed Select Technology -
> Performance Profile) level is changed. As a result, the ttarget value
> also becomes dyamic.
> 
> Improve the code to always get updated ttarget value.
> 
> Signed-off-by: Zhang Rui <rui.zhang@intel.com>

Applied to hwmon-next.

Thanks,
Guenter

> ---
>  drivers/hwmon/coretemp.c | 57 +++++++++++++++++++++++++++++-----------
>  1 file changed, 41 insertions(+), 16 deletions(-)
> 
> diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
> index 573ac8c5ed42..e537ab0d0422 100644
> --- a/drivers/hwmon/coretemp.c
> +++ b/drivers/hwmon/coretemp.c
> @@ -69,7 +69,6 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
>   */
>  struct temp_data {
>  	int temp;
> -	int ttarget;
>  	int tjmax;
>  	unsigned long last_updated;
>  	unsigned int cpu;
> @@ -303,6 +302,30 @@ static int get_tjmax(struct temp_data *tdata, struct device *dev)
>  	return tdata->tjmax;
>  }
>  
> +static int get_ttarget(struct temp_data *tdata, struct device *dev)
> +{
> +	u32 eax, edx;
> +	int tjmax, ttarget_offset, ret;
> +
> +	/*
> +	 * ttarget is valid only if tjmax can be retrieved from
> +	 * MSR_IA32_TEMPERATURE_TARGET
> +	 */
> +	if (tdata->tjmax)
> +		return -ENODEV;
> +
> +	ret = rdmsr_safe_on_cpu(tdata->cpu, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
> +	if (ret)
> +		return ret;
> +
> +	tjmax = (eax >> 16) & 0xff;
> +
> +	/* Read the still undocumented bits 8:15 of IA32_TEMPERATURE_TARGET. */
> +	ttarget_offset = (eax >> 8) & 0xff;
> +
> +	return (tjmax - ttarget_offset) * 1000;
> +}
> +
>  /* Keep track of how many zone pointers we allocated in init() */
>  static int max_zones __read_mostly;
>  /* Array of zone pointers. Serialized by cpu hotplug lock */
> @@ -356,8 +379,16 @@ static ssize_t show_ttarget(struct device *dev,
>  {
>  	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
>  	struct platform_data *pdata = dev_get_drvdata(dev);
> +	struct temp_data *tdata = pdata->core_data[attr->index];
> +	int ttarget;
>  
> -	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->ttarget);
> +	mutex_lock(&tdata->update_lock);
> +	ttarget = get_ttarget(tdata, dev);
> +	mutex_unlock(&tdata->update_lock);
> +
> +	if (ttarget < 0)
> +		return ttarget;
> +	return sprintf(buf, "%d\n", ttarget);
>  }
>  
>  static ssize_t show_temp(struct device *dev,
> @@ -466,7 +497,7 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
>  	struct platform_data *pdata = platform_get_drvdata(pdev);
>  	struct cpuinfo_x86 *c = &cpu_data(cpu);
>  	u32 eax, edx;
> -	int err, index, attr_no, tjmax;
> +	int err, index, attr_no;
>  
>  	/*
>  	 * Find attr number for sysfs:
> @@ -500,23 +531,17 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu,
>  	if (err)
>  		goto exit_free;
>  
> -	/* We can access status register. Get Critical Temperature */
> -	tjmax = get_tjmax(tdata, &pdev->dev);
> +	/* Make sure tdata->tjmax is a valid indicator for dynamic/static tjmax */
> +	get_tjmax(tdata, &pdev->dev);
>  
>  	/*
> -	 * Read the still undocumented bits 8:15 of IA32_TEMPERATURE_TARGET.
> -	 * The target temperature is available on older CPUs but not in this
> -	 * register. Atoms don't have the register at all.
> +	 * The target temperature is available on older CPUs but not in the
> +	 * MSR_IA32_TEMPERATURE_TARGET register. Atoms don't have the register
> +	 * at all.
>  	 */
> -	if (c->x86_model > 0xe && c->x86_model != 0x1c) {
> -		err = rdmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET,
> -					&eax, &edx);
> -		if (!err) {
> -			tdata->ttarget
> -			  = tjmax - ((eax >> 8) & 0xff) * 1000;
> +	if (c->x86_model > 0xe && c->x86_model != 0x1c)
> +		if (get_ttarget(tdata, &pdev->dev) >= 0)
>  			tdata->attr_size++;
> -		}
> -	}
>  
>  	pdata->core_data[attr_no] = tdata;
>