On 22-04-2025 08:52 pm, Andy Shevchenko wrote: > On Tue, Apr 22, 2025 at 08:45:31PM +0530, Aditya Garg wrote: >> On 22-04-2025 04:02 pm, Geert Uytterhoeven wrote: >>> On Tue, 22 Apr 2025 at 12:16, Andy Shevchenko >>> <andriy.shevchenko@xxxxxxxxxxxxxxx> wrote: > > ... > >>> 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. > > Can it use %p4cb? Or in another word, > why does it require "host" representation? Sven might know why. He is already CCed.
