From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: From: Irina Tirdea To: Jonathan Cameron , linux-iio@vger.kernel.org, Hartmut Knaack Cc: linux-kernel@vger.kernel.org, Vlad Dogaru , Irina Tirdea Subject: [PATCH v2 01/17] iio: accel: mma9553: fix endianness issue when reading status Date: Mon, 13 Apr 2015 18:40:48 +0300 Message-Id: <1428939664-12503-2-git-send-email-irina.tirdea@intel.com> In-Reply-To: <1428939664-12503-1-git-send-email-irina.tirdea@intel.com> References: <1428939664-12503-1-git-send-email-irina.tirdea@intel.com> List-ID: Refactor code for simplicity and clarity. This also fixes an endianness issue with the original code. When reading multiple registers, the received buffer of 16-bytes words is little endian (status, step count). On big endian machines, casting them to u32 would result in reversed order in the buffer (step count, status) leading to incorrect values for step count and activity. Signed-off-by: Irina Tirdea Reported-by: Hartmut Knaack --- drivers/iio/accel/mma9553.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/iio/accel/mma9553.c b/drivers/iio/accel/mma9553.c index 2df1af7..607dbfc 100644 --- a/drivers/iio/accel/mma9553.c +++ b/drivers/iio/accel/mma9553.c @@ -316,22 +316,19 @@ static int mma9553_set_config(struct mma9553_data *data, u16 reg, static int mma9553_read_activity_stepcnt(struct mma9553_data *data, u8 *activity, u16 *stepcnt) { - u32 status_stepcnt; - u16 status; + u16 buf[2]; int ret; ret = mma9551_read_status_words(data->client, MMA9551_APPID_PEDOMETER, - MMA9553_REG_STATUS, sizeof(u32), - (u16 *) &status_stepcnt); + MMA9553_REG_STATUS, sizeof(u32), buf); if (ret < 0) { dev_err(&data->client->dev, "error reading status and stepcnt\n"); return ret; } - status = status_stepcnt & MMA9553_MASK_CONF_WORD; - *activity = mma9553_get_bits(status, MMA9553_MASK_STATUS_ACTIVITY); - *stepcnt = status_stepcnt >> 16; + *activity = mma9553_get_bits(buf[0], MMA9553_MASK_STATUS_ACTIVITY); + *stepcnt = buf[1]; return 0; } -- 1.9.1