2022-09-29 11:08 GMT+09:00, Sergey Senozhatsky <senozhatsky@xxxxxxxxxxxx>:
> On (22/09/28 11:25), Tom Talpey wrote:
>> > diff --git a/fs/ksmbd/transport_tcp.c b/fs/ksmbd/transport_tcp.c
>> > index 143bba4e4db8..9b35afcdcf0d 100644
>> > --- a/fs/ksmbd/transport_tcp.c
>> > +++ b/fs/ksmbd/transport_tcp.c
>> > @@ -399,7 +399,8 @@ static int create_socket(struct interface *iface)
>> > ret = sock_create(PF_INET6, SOCK_STREAM, IPPROTO_TCP,
>> > &ksmbd_socket);
>> > if (ret) {
>> > - pr_err("Can't create socket for ipv6, try ipv4: %d\n", ret);
>> > + if (ret != -EAFNOSUPPORT)
>> > + pr_err("Can't create socket for ipv6, try ipv4: %d\n", ret);
>>
>> Why not just eliminate the splat? The only real error seems to be
>> that IPv6 is not configured, which is undoubtedly intentional, and
>> in any case there's nothing to do about it. Suggesting to "try ipv4"
>> is kind of pointless, isn't it?
>
> Yeah, that pr_err() sounds like a suggestion, but in fact it's not.
> It meant to say "ipv6 socket creation failed, fallback to ipv4".
I agree that it's better to change it to "fallback to ipv4" instead of
"try ipv4".
>
