Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Paul Fertser <fercerpav@gmail.com>
To:     linux-hwmon@vger.kernel.org
Cc:     Jean Delvare <jdelvare@suse.com>,
        Guenter Roeck <linux@roeck-us.net>,
        linux-kernel@vger.kernel.org, Paul Fertser <fercerpav@gmail.com>,
        stable@vger.kernel.org
Subject: [PATCH v2 1/3] hwmon: tmp421: handle I2C errors
Date:   Thu, 23 Sep 2021 12:47:59 +0300
Message-Id: <20210923094801.23332-1-fercerpav@gmail.com>
In-Reply-To: <20210922155323.GA3205709@roeck-us.net>
References: <20210922155323.GA3205709@roeck-us.net>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Function i2c_smbus_read_byte_data() can return a negative error number
instead of the data read if I2C transaction failed for whatever reason.

I consider this fix to be stable material as lack of error checking here
leads to serious issues on production hardware. Errors treated as
temperatures produce spurious critical temperature-crossed-threshold
errors in BMC logs for OCP server hardware. The patch was tested with
Mellanox OCP Mezzanine card emulating TMP421 protocol for temperature
sensing which sometimes leads to I2C protocol error during early boot up
stage.

Cc: stable@vger.kernel.org
Signed-off-by: Paul Fertser <fercerpav@gmail.com>
---

Changes from v1:
 - Reorganise code following excellent suggestion by Guenter Roeck
   to use tagged errors consistently

 drivers/hwmon/tmp421.c | 45 +++++++++++++++++++++++++++++++-----------
 1 file changed, 33 insertions(+), 12 deletions(-)

diff --git a/drivers/hwmon/tmp421.c b/drivers/hwmon/tmp421.c
index ede66ea6a730..63cb6badb478 100644
--- a/drivers/hwmon/tmp421.c
+++ b/drivers/hwmon/tmp421.c
@@ -93,7 +93,7 @@ struct tmp421_data {
 	struct hwmon_channel_info temp_info;
 	const struct hwmon_channel_info *info[2];
 	struct hwmon_chip_info chip;
-	char valid;
+	bool valid;
 	unsigned long last_updated;
 	unsigned long channels;
 	u8 config;
@@ -119,38 +119,59 @@ static int temp_from_u16(u16 reg)
 	return (temp * 1000 + 128) / 256;
 }
 
-static struct tmp421_data *tmp421_update_device(struct device *dev)
+static int tmp421_update_device(struct tmp421_data *data)
 {
-	struct tmp421_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
+	int ret = 0;
 	int i;
 
 	mutex_lock(&data->update_lock);
 
 	if (time_after(jiffies, data->last_updated + (HZ / 2)) ||
 	    !data->valid) {
-		data->config = i2c_smbus_read_byte_data(client,
-			TMP421_CONFIG_REG_1);
+		ret = i2c_smbus_read_byte_data(client,
+					       TMP421_CONFIG_REG_1);
+		if (ret < 0)
+			goto exit;
+		data->config = ret;
 
 		for (i = 0; i < data->channels; i++) {
-			data->temp[i] = i2c_smbus_read_byte_data(client,
-				TMP421_TEMP_MSB[i]) << 8;
-			data->temp[i] |= i2c_smbus_read_byte_data(client,
-				TMP421_TEMP_LSB[i]);
+			ret = i2c_smbus_read_byte_data(client,
+						       TMP421_TEMP_MSB[i]);
+			if (ret < 0)
+				goto exit;
+			data->temp[i] = ret << 8;
+
+			ret = i2c_smbus_read_byte_data(client,
+						       TMP421_TEMP_LSB[i]);
+			if (ret < 0)
+				goto exit;
+			data->temp[i] |= ret;
 		}
 		data->last_updated = jiffies;
-		data->valid = 1;
+		data->valid = true;
 	}
 
+exit:
 	mutex_unlock(&data->update_lock);
 
-	return data;
+	if (ret < 0) {
+		data->valid = false;
+		return ret;
+	}
+
+	return 0;
 }
 
 static int tmp421_read(struct device *dev, enum hwmon_sensor_types type,
 		       u32 attr, int channel, long *val)
 {
-	struct tmp421_data *tmp421 = tmp421_update_device(dev);
+	struct tmp421_data *tmp421 = dev_get_drvdata(dev);
+	int ret = 0;
+
+	ret = tmp421_update_device(tmp421);
+	if (ret)
+		return ret;
 
 	switch (attr) {
 	case hwmon_temp_input:
-- 
2.17.1