ice: read internal temperature sensor

Since 4.30 firmware exposes internal thermal sensor reading via admin
queue commands. Expose those readouts via hwmon API when supported.

Datasheet:

Get Sensor Reading Command (Opcode: 0x0632)

+--------------------+--------+--------------------+-------------------------+
| Name               | Bytes  | Value              |          Remarks        |
+--------------------+--------+--------------------+-------------------------+
| Flags              | 1-0    |                    |                         |
| Opcode             | 2-3    | 0x0632             | Command opcode          |
| Datalen            | 4-5    | 0                  | No external buffer.     |
| Return value       | 6-7    |                    | Return value.           |
| Cookie High        | 8-11   | Cookie             |                         |
| Cookie Low         | 12-15  | Cookie             |                         |
| Sensor             | 16     |                    | 0x00: Internal temp     |
|                    |        |                    | 0x01-0xFF: Reserved.    |
| Format             | 17     | Requested response | Only 0x00 is supported. |
|                    |        | format             | 0x01-0xFF: Reserved.    |
| Reserved           | 18-23  |                    |                         |
| Data Address high  | 24-27  | Response buffer    |                         |
|                    |        | address            |                         |
| Data Address low   | 28-31  | Response buffer    |                         |
|                    |        | address            |                         |
+--------------------+--------+--------------------+-------------------------+

Get Sensor Reading Response (Opcode: 0x0632)

+--------------------+--------+--------------------+-------------------------+
| Name               | Bytes  | Value              |          Remarks        |
+--------------------+--------+--------------------+-------------------------+
| Flags              | 1-0    |                    |                         |
| Opcode             | 2-3    | 0x0632             | Command opcode          |
| Datalen            | 4-5    | 0                  | No external buffer      |
| Return value       | 6-7    |                    | Return value.           |
|                    |        |                    | EINVAL: Invalid         |
|                    |        |                    | parameters              |
|                    |        |                    | ENOENT: Unsupported     |
|                    |        |                    | sensor                  |
|                    |        |                    | EIO: Sensor access      |
|                    |        |                    | error                   |
| Cookie High        | 8-11   | Cookie             |                         |
| Cookie Low         | 12-15  | Cookie             |                         |
| Sensor Reading     | 16-23  |                    | Format of the reading   |
|                    |        |                    | is dependent on request |
| Data Address high  | 24-27  | Response buffer    |                         |
|                    |        | address            |                         |
| Data Address low   | 28-31  | Response buffer    |                         |
|                    |        | address            |                         |
+--------------------+--------+--------------------+-------------------------+

Sensor Reading for Sensor 0x00 (Internal Chip Temperature):

+--------------------+--------+--------------------+-------------------------+
| Name               | Bytes  | Value              |          Remarks        |
+--------------------+--------+--------------------+-------------------------+
| Thermal Sensor     | 0      |                    | Reading in degrees      |
| reading            |        |                    | Celsius. Signed int8    |
| Warning High       | 1      |                    | Warning High threshold  |
| threshold          |        |                    | in degrees Celsius.     |
|                    |        |                    | Unsigned int8.          |
|                    |        |                    | 0xFF when unsupported   |
| Critical High      | 2      |                    | Critical High threshold |
| threshold          |        |                    | in degrees Celsius.     |
|                    |        |                    | Unsigned int8.          |
|                    |        |                    | 0xFF when unsupported   |
| Fatal High         | 3      |                    | Fatal High threshold    |
| threshold          |        |                    | in degrees Celsius.     |
|                    |        |                    | Unsigned int8.          |
|                    |        |                    | 0xFF when unsupported   |
| Reserved           | 4-7    |                    |                         |
+--------------------+--------+--------------------+-------------------------+

Driver provides current reading from HW as well as device specific
thresholds for thermal alarm (Warning, Critical, Fatal) events.

$ sensors

Output
=========================================================
ice-pci-b100
Adapter: PCI adapter
temp1:        +62.0°C  (high = +95.0°C, crit = +105.0°C)
                       (emerg = +115.0°C)

Tested on Intel Corporation Ethernet Controller E810-C for SFP

Co-developed-by: Marcin Domagala <marcinx.domagala@intel.com>
Signed-off-by: Marcin Domagala <marcinx.domagala@intel.com>
Co-developed-by: Eric Joyner <eric.joyner@intel.com>
Signed-off-by: Eric Joyner <eric.joyner@intel.com>
Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Konrad Knitter <konrad.knitter@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

1 files changed, 126 insertions, 0 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_hwmon.c b/drivers/net/ethernet/intel/ice/ice_hwmon.c
new file mode 100644
index 000000000000..e4c2c1bff6c0
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_hwmon.c
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023, Intel Corporation. */
+
+#include "ice.h"
+#include "ice_hwmon.h"
+#include "ice_adminq_cmd.h"
+
+#include <linux/hwmon.h>
+
+#define TEMP_FROM_REG(reg) ((reg) * 1000)
+
+static const struct hwmon_channel_info *ice_hwmon_info[] = {
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT | HWMON_T_MAX |
+			   HWMON_T_CRIT | HWMON_T_EMERGENCY),
+	NULL
+};
+
+static int ice_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+			  u32 attr, int channel, long *val)
+{
+	struct ice_aqc_get_sensor_reading_resp resp;
+	struct ice_pf *pf = dev_get_drvdata(dev);
+	int ret;
+
+	if (type != hwmon_temp)
+		return -EOPNOTSUPP;
+
+	ret = ice_aq_get_sensor_reading(&pf->hw, &resp);
+	if (ret) {
+		dev_warn_ratelimited(dev,
+				     "%s HW read failure (%d)\n",
+				     __func__,
+				     ret);
+		return ret;
+	}
+
+	switch (attr) {
+	case hwmon_temp_input:
+		*val = TEMP_FROM_REG(resp.data.s0f0.temp);
+		break;
+	case hwmon_temp_max:
+		*val = TEMP_FROM_REG(resp.data.s0f0.temp_warning_threshold);
+		break;
+	case hwmon_temp_crit:
+		*val = TEMP_FROM_REG(resp.data.s0f0.temp_critical_threshold);
+		break;
+	case hwmon_temp_emergency:
+		*val = TEMP_FROM_REG(resp.data.s0f0.temp_fatal_threshold);
+		break;
+	default:
+		dev_dbg(dev, "%s unsupported attribute (%d)\n",
+			__func__, attr);
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static umode_t ice_hwmon_is_visible(const void *data,
+				    enum hwmon_sensor_types type, u32 attr,
+				    int channel)
+{
+	if (type != hwmon_temp)
+		return 0;
+
+	switch (attr) {
+	case hwmon_temp_input:
+	case hwmon_temp_crit:
+	case hwmon_temp_max:
+	case hwmon_temp_emergency:
+		return 0444;
+	}
+
+	return 0;
+}
+
+static const struct hwmon_ops ice_hwmon_ops = {
+	.is_visible = ice_hwmon_is_visible,
+	.read = ice_hwmon_read
+};
+
+static const struct hwmon_chip_info ice_chip_info = {
+	.ops = &ice_hwmon_ops,
+	.info = ice_hwmon_info
+};
+
+static bool ice_is_internal_reading_supported(struct ice_pf *pf)
+{
+	/* Only the first PF will report temperature for a chip.
+	 * Note that internal temp reading is not supported
+	 * for older FW (< v4.30).
+	 */
+	if (pf->hw.pf_id)
+		return false;
+
+	unsigned long sensors = pf->hw.dev_caps.supported_sensors;
+
+	return _test_bit(ICE_SENSOR_SUPPORT_E810_INT_TEMP_BIT, &sensors);
+};
+
+void ice_hwmon_init(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	struct device *hdev;
+
+	if (!ice_is_internal_reading_supported(pf))
+		return;
+
+	hdev = hwmon_device_register_with_info(dev, "ice", pf, &ice_chip_info,
+					       NULL);
+	if (IS_ERR(hdev)) {
+		dev_warn(dev,
+			 "hwmon_device_register_with_info returns error (%ld)",
+			 PTR_ERR(hdev));
+		return;
+	}
+	pf->hwmon_dev = hdev;
+}
+
+void ice_hwmon_exit(struct ice_pf *pf)
+{
+	if (!pf->hwmon_dev)
+		return;
+	hwmon_device_unregister(pf->hwmon_dev);
+}