On 03. 03. 22, 8:45, Greg KH wrote:
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.
Note this was missed as this driver was added only few days ago, so it
was not covered by kbuild against my tree until then. And to me, it
looks like kbuild is run on my tree only when it has nothing better to
do (which is perfectly fine, as even that catches a lot of things).
Besides that, there are two places in the driver which need update.
So should I send a v4 or wait?
thanks,
--
js
suse labs
