Re: [PATCH v3] serial: make uart_console_write->putchar()'s character an unsigned char
From: Greg KH
Date: Thu Mar 03 2022 - 02:45:28 EST
On Thu, Mar 03, 2022 at 07:32:59AM +0100, Jiri Slaby wrote:
> On 02. 03. 22, 8:27, Jiri Slaby wrote:
> > Currently, uart_console_write->putchar's second parameter (the
> > character) is of type int. It makes little sense, provided uart_console_write()
> > accepts the input string as "const char *s" and passes its content -- the
> > characters -- to putchar(). So switch the character's type to unsigned
> > char.
> >
> > We don't use char as that is signed on some platforms. That would cause
> > troubles for drivers which (implicitly) cast the char to u16 when
> > writing to the device. Sign extension would happen in that case and the
> > value written would be completely different to the provided char. DZ is
> > an example of such a driver -- on MIPS, it uses u16 for dz_out in
> > dz_console_putchar().
> >
> > Note we do the char -> uchar conversion implicitly in
> > uart_console_write(). Provided we do not change size of the data type,
> > sign extension does not happen there, so the problem is void.
> >
> > This makes the types consistent and unified with the rest of the uart
> > layer, which uses unsigned char in most places already. One exception is
> > xmit_buf, but that is going to be converted later.
>
> Kbuild seems to serve me this one by one. So this patch is still incomplete:
> > drivers/tty/serial/sunplus-uart.c:526:7: error: incompatible function
> pointer types passing 'void (struct uart_port *, int)' to parameter of type
> 'void (*)(struct uart_port *, unsigned char)'
Let me just add this to my -testing branch, that will give us much
quicker kbuild responses and handle stuff like this easier and I can fix
the errors up when they are reported.
thanks,
greg k-h