mfd: qnap-mcu: Add proper error handling for command errors

Further investigation revealed that the MCU in QNAP devices may return
two error states. One "@8" for a checksum error in the submitted command
and one "@9" for any generic (and sadly unspecified) error.

These error codes with 2 data character can of course also be shorter
then the expected reply length for the submitted command, so we'll
need to check the received data for error codes and exit the receive
portion early in that case.

Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20251113165218.449616-5-heiko@sntech.de
Signed-off-by: Lee Jones <lee@kernel.org>

diff --git a/drivers/mfd/qnap-mcu.c b/drivers/mfd/qnap-mcu.c
index 558c3bc07ed392e4dc00f6a7f5322701bbd1ca71..6bbf8334caa454e7e80f07e04168391591a27364 100644 (file)
--- a/drivers/mfd/qnap-mcu.c
+++ b/drivers/mfd/qnap-mcu.c
@@ -19,6 +19,7 @@
 /* The longest command found so far is 5 bytes long */
 #define QNAP_MCU_MAX_CMD_SIZE          5
 #define QNAP_MCU_MAX_DATA_SIZE         36
+#define QNAP_MCU_ERROR_SIZE            2
 #define QNAP_MCU_CHECKSUM_SIZE         1
 
 #define QNAP_MCU_RX_BUFFER_SIZE                \
@@ -103,6 +104,48 @@ static int qnap_mcu_write(struct qnap_mcu *mcu, const u8 *data, u8 data_size)
        return serdev_device_write(mcu->serdev, tx, length, HZ);
 }
 
+static bool qnap_mcu_is_error_msg(size_t size)
+{
+       return (size == QNAP_MCU_ERROR_SIZE + QNAP_MCU_CHECKSUM_SIZE);
+}
+
+static bool qnap_mcu_reply_is_generic_error(unsigned char *buf, size_t size)
+{
+       if (!qnap_mcu_is_error_msg(size))
+               return false;
+
+       if (buf[0] == '@' && buf[1] == '9')
+               return true;
+
+       return false;
+}
+
+static bool qnap_mcu_reply_is_checksum_error(unsigned char *buf, size_t size)
+{
+       if (!qnap_mcu_is_error_msg(size))
+               return false;
+
+       if (buf[0] == '@' && buf[1] == '8')
+               return true;
+
+       return false;
+}
+
+static bool qnap_mcu_reply_is_any_error(struct qnap_mcu *mcu, unsigned char *buf, size_t size)
+{
+       if (qnap_mcu_reply_is_generic_error(buf, size)) {
+               dev_err(&mcu->serdev->dev, "Controller sent generic error response\n");
+               return true;
+       }
+
+       if (qnap_mcu_reply_is_checksum_error(buf, size)) {
+               dev_err(&mcu->serdev->dev, "Controller received invalid checksum for the command\n");
+               return true;
+       }
+
+       return false;
+}
+
 static size_t qnap_mcu_receive_buf(struct serdev_device *serdev, const u8 *buf, size_t size)
 {
        struct device *dev = &serdev->dev;
@@ -136,6 +179,24 @@ static size_t qnap_mcu_receive_buf(struct serdev_device *serdev, const u8 *buf,
                }
        }
 
+       /*
+        * We received everything the uart had to offer for now.
+        * This could mean that either the uart will send more in a 2nd
+        * receive run, or that the MCU cut the reply short because it
+        * sent an error code instead of the expected reply.
+        *
+        * So check if the received data has the correct size for an error
+        * reply and if it matches, is an actual error code.
+        */
+       if (qnap_mcu_is_error_msg(reply->received) &&
+           qnap_mcu_verify_checksum(reply->data, reply->received) &&
+           qnap_mcu_reply_is_any_error(mcu, reply->data, reply->received)) {
+               /* The reply was an error code, we're done */
+               reply->length = 0;
+
+               complete(&reply->done);
+       }
+
        /*
         * The only way to get out of the above loop and end up here
         * is through consuming all of the supplied data, so here we
@@ -182,10 +243,13 @@ int qnap_mcu_exec(struct qnap_mcu *mcu,
        }
 
        if (!qnap_mcu_verify_checksum(rx, reply->received)) {
-               dev_err(&mcu->serdev->dev, "Invalid Checksum received\n");
+               dev_err(&mcu->serdev->dev, "Invalid Checksum received from controller\n");
                return -EPROTO;
        }
 
+       if (qnap_mcu_reply_is_any_error(mcu, rx, reply->received))
+               return -EPROTO;
+
        memcpy(reply_data, rx, reply_data_size);
 
        return 0;