[PATCH net-next v3 6/6] eth: fbnic: firmware notifies hwmon on sensor threshold events

[Zinc Lim <limzhineng2@gmail.com>]

The firmware sends an unsolicited message via the new
FBNIC_TLV_MSG_ID_SENSOR_THRESHOLD_EXCEEDED_RESP IPC message when a
temperature or voltage sensor crosses one of its thresholds. Parse this
message and translate it into the corresponding hwmon alarm
(temp1_{min,max,crit}_alarm or in0_{min,max}_alarm) via
hwmon_notify_event(), so userspace listeners are woken on the relevant
sysfs attribute.

fbnic_hwmon_notify_event() is driven from the FW mailbox IRQ path, so it
can run concurrently with hwmon registration and teardown. Guard the
publish/teardown of fbd->hwmon: register publishes it with WRITE_ONCE()
only after a successful registration (and leaves it NULL on failure),
unregister clears it with WRITE_ONCE(NULL) and then
synchronize_irq(fbd->fw_msix_vector) to drain any in-flight mailbox IRQ
before unregistering, and notify_event reads it once with READ_ONCE() and
skips the notification when it is NULL.

Signed-off-by: Zinc Lim <limzhineng2@gmail.com>
---
 drivers/net/ethernet/meta/fbnic/fbnic.h       |  1 +
 drivers/net/ethernet/meta/fbnic/fbnic_fw.c    | 54 ++++++++++++++
 drivers/net/ethernet/meta/fbnic/fbnic_fw.h    |  9 +++
 drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c | 71 ++++++++++++++++---
 4 files changed, 127 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h
index f647ef07704b..4a49c20e4a01 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic.h
@@ -192,6 +192,7 @@ void fbnic_fw_free_mbx(struct fbnic_dev *fbd);
 
 void fbnic_hwmon_register(struct fbnic_dev *fbd);
 void fbnic_hwmon_unregister(struct fbnic_dev *fbd);
+void fbnic_hwmon_notify_event(struct fbnic_dev *fbd, int id, long val);
 
 int fbnic_mac_request_irq(struct fbnic_dev *fbd);
 void fbnic_mac_free_irq(struct fbnic_dev *fbd);
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index e5669dfd9790..fd96a3962e3f 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -1639,6 +1639,57 @@ fbnic_fw_parser_test(void *opaque, struct fbnic_tlv_msg **results)
 	return err;
 }
 
+static const struct fbnic_tlv_index fbnic_threshold_exceeded_resp_index[] = {
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_TSENE_THERM_EXCEEDED_FLAG),
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_TSENE_VOLT_EXCEEDED_FLAG),
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_TSENE_THERMAL),
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_TSENE_VOLTAGE),
+	FBNIC_TLV_ATTR_LAST
+};
+
+static int fbnic_fw_parse_threshold_exceeded_resp(void *opaque,
+						  struct fbnic_tlv_msg **results)
+{
+	bool therm_exceeded, volt_exceeded;
+	struct fbnic_dev *fbd = opaque;
+	s32 value;
+
+	therm_exceeded =
+		fta_get_sint(results, FBNIC_FW_TSENE_THERM_EXCEEDED_FLAG);
+	volt_exceeded =
+		fta_get_sint(results, FBNIC_FW_TSENE_VOLT_EXCEEDED_FLAG);
+
+	if (!therm_exceeded && !volt_exceeded) {
+		dev_err(fbd->dev,
+			"Threshold exceeded message with no flag set\n");
+		return -EINVAL;
+	}
+
+	if (therm_exceeded) {
+		if (!results[FBNIC_FW_TSENE_THERMAL]) {
+			dev_err(fbd->dev,
+				"Thermal threshold exceeded but no value received\n");
+			return -EINVAL;
+		}
+		value = fta_get_sint(results, FBNIC_FW_TSENE_THERMAL);
+		dev_err(fbd->dev, "Thermal threshold exceeded: %d mC\n", value);
+		fbnic_hwmon_notify_event(fbd, FBNIC_SENSOR_TEMP, value);
+	}
+
+	if (volt_exceeded) {
+		if (!results[FBNIC_FW_TSENE_VOLTAGE]) {
+			dev_err(fbd->dev,
+				"Voltage threshold exceeded but no value received\n");
+			return -EINVAL;
+		}
+		value = fta_get_sint(results, FBNIC_FW_TSENE_VOLTAGE);
+		dev_err(fbd->dev, "Voltage threshold exceeded: %d mV\n", value);
+		fbnic_hwmon_notify_event(fbd, FBNIC_SENSOR_VOLTAGE, value);
+	}
+
+	return 0;
+}
+
 static const struct fbnic_tlv_parser fbnic_fw_tlv_parser[] = {
 	FBNIC_TLV_PARSER(TEST, fbnic_tlv_test_index, fbnic_fw_parser_test),
 	FBNIC_TLV_PARSER(FW_CAP_RESP, fbnic_fw_cap_resp_index,
@@ -1667,6 +1718,9 @@ static const struct fbnic_tlv_parser fbnic_fw_tlv_parser[] = {
 	FBNIC_TLV_PARSER(TSENE_READ_RESP,
 			 fbnic_tsene_read_resp_index,
 			 fbnic_fw_parse_tsene_read_resp),
+	FBNIC_TLV_PARSER(SENSOR_THRESHOLD_EXCEEDED_RESP,
+			 fbnic_threshold_exceeded_resp_index,
+			 fbnic_fw_parse_threshold_exceeded_resp),
 	FBNIC_TLV_PARSER(LOG_MSG_REQ,
 			 fbnic_fw_log_req_index,
 			 fbnic_fw_parse_log_req),
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
index 68ffd49e0cdd..87301e608255 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
@@ -227,6 +227,7 @@ enum {
 	FBNIC_TLV_MSG_ID_QSFP_READ_RESP			= 0x39,
 	FBNIC_TLV_MSG_ID_TSENE_READ_REQ			= 0x3C,
 	FBNIC_TLV_MSG_ID_TSENE_READ_RESP		= 0x3D,
+	FBNIC_TLV_MSG_ID_SENSOR_THRESHOLD_EXCEEDED_RESP = 0x40,
 	FBNIC_TLV_MSG_ID_LOG_SEND_LOGS_REQ		= 0x43,
 	FBNIC_TLV_MSG_ID_LOG_MSG_REQ			= 0x44,
 	FBNIC_TLV_MSG_ID_LOG_MSG_RESP			= 0x45,
@@ -296,6 +297,14 @@ enum {
 	FBNIC_FW_TSENE_MSG_MAX
 };
 
+enum {
+	FBNIC_FW_TSENE_THERM_EXCEEDED_FLAG	= 0x0,
+	FBNIC_FW_TSENE_VOLT_EXCEEDED_FLAG	= 0x1,
+	FBNIC_FW_TSENE_THERMAL			= 0x2,
+	FBNIC_FW_TSENE_VOLTAGE			= 0x3,
+	FBNIC_FW_TSENE_EXCEEDED_MSG_MAX,
+};
+
 enum {
 	FBNIC_FW_OWNERSHIP_FLAG			= 0x0,
 	FBNIC_FW_OWNERSHIP_TIME			= 0x1,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c b/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c
index 11fa8aab0f5b..2dff59bc0e8b 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c
@@ -206,6 +206,8 @@ static const struct hwmon_chip_info fbnic_chip_info = {
 
 void fbnic_hwmon_register(struct fbnic_dev *fbd)
 {
+	struct device *hwmon;
+
 	if (!IS_REACHABLE(CONFIG_HWMON))
 		return;
 
@@ -213,22 +215,75 @@ void fbnic_hwmon_register(struct fbnic_dev *fbd)
 	fbd->hwmon_cache.temp_mdeg = FBNIC_SENSOR_NO_DATA;
 	fbd->hwmon_cache.volt_mv = FBNIC_SENSOR_NO_DATA;
 
-	fbd->hwmon = hwmon_device_register_with_info(fbd->dev, "fbnic",
-						     fbd, &fbnic_chip_info,
-						     NULL);
-	if (IS_ERR(fbd->hwmon)) {
+	hwmon = hwmon_device_register_with_info(fbd->dev, "fbnic", fbd,
+						&fbnic_chip_info, NULL);
+	if (IS_ERR(hwmon)) {
 		dev_notice(fbd->dev,
 			   "Failed to register hwmon device %pe\n",
-			   fbd->hwmon);
-		fbd->hwmon = NULL;
+			   hwmon);
+		return;
 	}
+
+	WRITE_ONCE(fbd->hwmon, hwmon);
 }
 
 void fbnic_hwmon_unregister(struct fbnic_dev *fbd)
 {
+	struct device *hwmon;
+
 	if (!IS_REACHABLE(CONFIG_HWMON) || !fbd->hwmon)
 		return;
 
-	hwmon_device_unregister(fbd->hwmon);
-	fbd->hwmon = NULL;
+	hwmon = fbd->hwmon;
+	/* Pair with READ_ONCE() in fbnic_hwmon_notify_event(). Publish NULL
+	 * and wait for any in-flight FW mailbox IRQ handler to finish so it
+	 * cannot dereference the hwmon device after we unregister it.
+	 */
+	WRITE_ONCE(fbd->hwmon, NULL);
+	synchronize_irq(fbd->fw_msix_vector);
+
+	hwmon_device_unregister(hwmon);
+}
+
+void fbnic_hwmon_notify_event(struct fbnic_dev *fbd, int id, long val)
+{
+	enum hwmon_sensor_types type;
+	struct device *hwmon;
+	s32 attr = -1;
+
+	if (!IS_REACHABLE(CONFIG_HWMON))
+		return;
+
+	switch (id) {
+	case FBNIC_SENSOR_TEMP:
+		type = hwmon_temp;
+
+		if (val <= fbd->fw_cap.temp.min)
+			attr = hwmon_temp_min_alarm;
+		else if (val >= fbd->fw_cap.temp.crit)
+			attr = hwmon_temp_crit_alarm;
+		else if (val >= fbd->fw_cap.temp.max)
+			attr = hwmon_temp_max_alarm;
+
+		break;
+	case FBNIC_SENSOR_VOLTAGE:
+		type = hwmon_in;
+
+		if (val <= fbd->fw_cap.volt.min)
+			attr = hwmon_in_min_alarm;
+		else if (val >= fbd->fw_cap.volt.max)
+			attr = hwmon_in_max_alarm;
+
+		break;
+	default:
+		return;
+	}
+
+	/* Pair with WRITE_ONCE() in fbnic_hwmon_unregister(). Skip the
+	 * notification if hwmon failed to register or has already been torn
+	 * down.
+	 */
+	hwmon = READ_ONCE(fbd->hwmon);
+	if (attr >= 0 && hwmon)
+		hwmon_notify_event(hwmon, type, attr, 0);
 }
-- 
2.53.0-Meta