On Wed, Sep 29, 2021 at 04:26:08PM +0100, John Keeping wrote:
> I have a ST1633 touch controller which fails to probe due to a timeout
> waiting for the controller to become ready. Increasing the minimum
> delay to 100ms ensures that the probe sequence completes successfully.
>
> The ST1633 datasheet says nothing about the maximum delay here and the
> ST1232 I2C protocol document says "wait until" with no notion of a
> timeout.
>
> Since this only runs once during probe, being generous with the timout
> seems reasonable and most likely the device will become ready
> eventually.
I'll apply this, but I wonder if it would not make sense to mark the
driver as preferring asynchronous probing, so we do not delay
initializing other devices while we are waiting for the touch controller
to reset? Could you send me a patch for that?
>
> (It may be worth noting that I saw this issue with a PREEMPT_RT patched
> kernel which probably has tighter wakeups from usleep_range() than other
> preemption models.)
>
> Fixes: f605be6a57b4 ("Input: st1232 - wait until device is ready before reading resolution")
> Signed-off-by: John Keeping <john@xxxxxxxxxxxx>
> ---
> drivers/input/touchscreen/st1232.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/input/touchscreen/st1232.c b/drivers/input/touchscreen/st1232.c
> index 6abae665ca71..9d1dea6996a2 100644
> --- a/drivers/input/touchscreen/st1232.c
> +++ b/drivers/input/touchscreen/st1232.c
> @@ -92,7 +92,7 @@ static int st1232_ts_wait_ready(struct st1232_ts_data *ts)
> unsigned int retries;
> int error;
>
> - for (retries = 10; retries; retries--) {
> + for (retries = 100; retries; retries--) {
> error = st1232_ts_read_data(ts, REG_STATUS, 1);
> if (!error) {
> switch (ts->read_buf[0]) {
> --
> 2.33.0
>
Thanks.
--
Dmitry
