[PATCH v4 1/3] lib/vsprintf: Add support for generic FourCCs by extending %p4cc
Aditya Garg
gargaditya08 at live.com
Tue Apr 22 15:15:31 UTC 2025
On 22-04-2025 04:02 pm, Geert Uytterhoeven wrote:
> Hi Andy,
>
> On Tue, 22 Apr 2025 at 12:16, Andy Shevchenko
> <andriy.shevchenko at linux.intel.com> wrote:
>> On Tue, Apr 22, 2025 at 10:43:59AM +0200, Geert Uytterhoeven wrote:
>>> On Tue, 22 Apr 2025 at 10:30, Aditya Garg <gargaditya08 at live.com> wrote:
>>>> On 22-04-2025 01:37 pm, Geert Uytterhoeven wrote:
>>>>> On Tue, 8 Apr 2025 at 08:48, Aditya Garg <gargaditya08 at live.com> wrote:
>>
>> ...
>>
>>>> Originally, it was %p4cr (reverse-endian), but on the request of the
>>>> maintainers, it was changed to %p4cn.
>>>
>>> Ah, I found it[1]:
>>>
>>> | so, it needs more information that this mimics htonl() / ntohl() for
>>> networking.
>>>
>>> IMHO this does not mimic htonl(), as htonl() is a no-op on big-endian.
>>> while %p4ch and %p4cl yield different results on big-endian.
>>>
>>>> So here network means reverse of host, not strictly big-endian.
>>>
>>> Please don't call it "network byte order" if that does not have the same
>>> meaning as in the network subsystem.
>>>
>>> Personally, I like "%p4r" (reverse) more...
>>> (and "%p4ch" might mean human-readable ;-)
>>
>> It will confuse the reader. h/r is not very established pair. If you really
>> wont see h/n, better to drop them completely for now then. Because I'm against
>> h/r pair.
>
> I am not against h/n in se, but I am against bad/confusing naming.
> The big question is: should it print
> (A) the value in network byte order, or
> (B) the reverse of host byte order?
>
> If the answer is (A), I see no real reason to have %p4n, as %p4b prints
> the exact same thing. Moreover, it leaves us without a portable
> way to print values in reverse without the caller doing an explicit
> __swab32() (which is not compatible with the %p pass-by-pointer
> calling convention).
>
> If the answer is (B), "%p4n using network byte order" is bad/confusing
> naming.
The answer is definitely (B). As far as bad/confusing naming is concerned,
I'll let vsprintf maintainers decide. As far as usage is concerned, %p4cl
is used in appletbdrm and %p4ch is used in to be upstreamed soon smc driver
by Asahi Linux.
More information about the dri-devel
mailing list