lkml.org 
[lkml]   [2021]   [Sep]   [2]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 3/3] k10temp: Add power sensor for family 19h
Date
On newer Fam19h server line of AMD processors a new channel
is created to report and manage socket power limits.

This patch creates hwmon_power sensor to report current power,
power cap and max power cap of the socket.
While at it, update the k10temp documentation

Tested-by: suma hegde <suma.hegde@amd.com>
Signed-off-by: Naveen Krishna Chatradhi <nchatrad@amd.com>
Cc: Guenter Roeck <linux@roeck-us.net>
---
Documentation/hwmon/k10temp.rst | 18 ++++++
drivers/hwmon/k10temp.c | 106 ++++++++++++++++++++++++++++++++
2 files changed, 124 insertions(+)

diff --git a/Documentation/hwmon/k10temp.rst b/Documentation/hwmon/k10temp.rst
index 91b99adc6c48..d5a78a7b6ca5 100644
--- a/Documentation/hwmon/k10temp.rst
+++ b/Documentation/hwmon/k10temp.rst
@@ -132,3 +132,21 @@ On Family 17h and Family 18h CPUs, additional temperature sensors may report
Core Complex Die (CCD) temperatures. Up to 8 such temperatures are reported
as temp{3..10}_input, labeled Tccd{1..8}. Actual support depends on the CPU
variant.
+
+On Family 19h server line of CPUs, additionally driver may report socket
+current power consumption with power cap and power cap max. This requires the
+HSMP support exported in the amd_nb module.
+
+The power1_cap can be set to any value, SMU FW will limit the maximum cap to
+the value reported by power1_cap_max entry. The SMU FW may not take any action
+if the power1_cap is set to a value lesser than the minimum socket consumption.
+
+The following attributes may be reported.
+
+================ ===== ========================================================
+Name Perm Description
+================ ===== ========================================================
+power1_input RO Socket current Power consumed
+power1_cap RW Socket Power limit can be set between 0 and power1_cap_max
+power1_cap_max RO Maximum powerlimit calculated and reported by the SMU FW
+================ ===== ========================================================
diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index 3618a924e78e..b993fdd94979 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -105,6 +105,9 @@ struct k10temp_data {
u32 show_temp;
bool is_zen;
u32 ccd_offset;
+ bool show_power;
+ char pwr_label[20];
+ u32 power_cap_max;
};

#define TCTL_BIT 0
@@ -197,10 +200,14 @@ static int k10temp_read_labels(struct device *dev,
enum hwmon_sensor_types type,
u32 attr, int channel, const char **str)
{
+ struct k10temp_data *data = dev_get_drvdata(dev);
switch (type) {
case hwmon_temp:
*str = k10temp_temp_label[channel];
break;
+ case hwmon_power:
+ *str = data->pwr_label;
+ break;
default:
return -EOPNOTSUPP;
}
@@ -254,12 +261,43 @@ static int k10temp_read_temp(struct device *dev, u32 attr, int channel,
return 0;
}

+static int k10temp_read_power(struct device *dev, u32 attr, int channel, long *val)
+{
+ struct k10temp_data *data = dev_get_drvdata(dev);
+ struct hsmp_message msg = { 0 };
+ int err;
+
+ switch (attr) {
+ case hwmon_power_input:
+ msg.msg_id = HSMP_GET_SOCKET_POWER;
+ break;
+ case hwmon_power_cap:
+ msg.msg_id = HSMP_GET_SOCKET_POWER_LIMIT;
+ break;
+ case hwmon_power_cap_max:
+ /* power_cap_max does not change dynamically, hence return the cached value */
+ *val = data->power_cap_max * 1000;
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+ msg.response_sz = 1;
+ err = hsmp_send_message(amd_pci_dev_to_node_id(data->pdev), &msg);
+ if (!err)
+ /* power metric is reported in micro watts. hence multiply by 1000 */
+ *val = msg.response[0] * 1000;
+
+ return err;
+}
+
static int k10temp_read(struct device *dev, enum hwmon_sensor_types type,
u32 attr, int channel, long *val)
{
switch (type) {
case hwmon_temp:
return k10temp_read_temp(dev, attr, channel, val);
+ case hwmon_power:
+ return k10temp_read_power(dev, attr, channel, val);
default:
return -EOPNOTSUPP;
}
@@ -308,12 +346,45 @@ static umode_t k10temp_is_visible(const void *_data,
return 0;
}
break;
+ case hwmon_power:
+ switch (attr) {
+ case hwmon_power_input:
+ case hwmon_power_cap_max:
+ case hwmon_power_label:
+ /* Show power attributes only if show_power is available */
+ if (data->show_power)
+ break;
+ return 0;
+ case hwmon_power_cap:
+ if (data->show_power)
+ return 0644;
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+ break;
default:
return 0;
}
return 0444;
}

+static int k10temp_write(struct device *dev, enum hwmon_sensor_types type,
+ u32 attr, int channel, long val)
+{
+ struct hsmp_message msg = { 0 };
+ struct k10temp_data *data = dev_get_drvdata(dev);
+
+ if (type == hwmon_power && attr == hwmon_power_cap) {
+ msg.response_sz = 1;
+ msg.num_args = 1;
+ msg.msg_id = HSMP_SET_SOCKET_POWER_LIMIT;
+ msg.args[0] = val / 1000;
+ return hsmp_send_message(amd_pci_dev_to_node_id(data->pdev), &msg);
+ }
+ return -EOPNOTSUPP;
+}
+
static bool has_erratum_319(struct pci_dev *pdev)
{
u32 pkg_type, reg_dram_cfg;
@@ -362,6 +433,9 @@ static const struct hwmon_channel_info *k10temp_info[] = {
HWMON_T_INPUT | HWMON_T_LABEL,
HWMON_T_INPUT | HWMON_T_LABEL,
HWMON_T_INPUT | HWMON_T_LABEL),
+ HWMON_CHANNEL_INFO(power,
+ HWMON_P_INPUT | HWMON_P_LABEL |
+ HWMON_P_CAP | HWMON_P_CAP_MAX),
NULL
};

@@ -369,6 +443,7 @@ static const struct hwmon_ops k10temp_hwmon_ops = {
.is_visible = k10temp_is_visible,
.read = k10temp_read,
.read_string = k10temp_read_labels,
+ .write = k10temp_write,
};

static const struct hwmon_chip_info k10temp_chip_info = {
@@ -390,6 +465,32 @@ static void k10temp_get_ccd_support(struct pci_dev *pdev,
}
}

+static int k10temp_get_max_power(struct k10temp_data *data)
+{
+ int err;
+ struct hsmp_message msg = { 0 };
+
+ msg.msg_id = HSMP_GET_SOCKET_POWER_LIMIT_MAX;
+ msg.response_sz = 1;
+ err = hsmp_send_message(amd_pci_dev_to_node_id(data->pdev), &msg);
+ if (!err)
+ data->power_cap_max = msg.response[0];
+ return err;
+}
+
+static void check_power_support(struct k10temp_data *data)
+{
+ /* HSMP support is required to obtain power metrics */
+ if (!amd_nb_has_feature(AMD_NB_HSMP))
+ return;
+
+ if (k10temp_get_max_power(data))
+ return;
+
+ sprintf(data->pwr_label, "socket%d_pwr", amd_pci_dev_to_node_id(data->pdev));
+ data->show_power = true;
+}
+
static int k10temp_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
int unreliable = has_erratum_319(pdev);
@@ -448,6 +549,11 @@ static int k10temp_probe(struct pci_dev *pdev, const struct pci_device_id *id)

switch (boot_cpu_data.x86_model) {
case 0x0 ... 0x1: /* Zen3 SP3/TR */
+ case 0x30 ... 0x31:
+ check_power_support(data);
+ data->ccd_offset = 0x154;
+ k10temp_get_ccd_support(pdev, data, 8);
+ break;
case 0x21: /* Zen3 Ryzen Desktop */
case 0x50 ... 0x5f: /* Green Sardine */
data->ccd_offset = 0x154;
--
2.17.1
\
 
 \ /
  Last update: 2021-09-02 19:45    [W:0.711 / U:0.012 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site