Re: [RFCv7 PATCH net-next 36/36] net: redefine the prototype of netdev_features_t

["shenjian (K)" <shenjian15@huawei.com>]

在 2022/8/11 23:13, Jakub Kicinski 写道:
> On Thu, 11 Aug 2022 15:07:57 +0200 Alexander Lobakin wrote:
>
>>> Yes, Jakub also mentioned this.
>>>
>>> But there are many existed features interfaces(e.g. ndo_fix_features,
>>> ndo_features_check), use netdev_features_t as return value. Then we
>>> have to change their prototype.
>> We have to do 12k lines of changes already :D
>> You know, 16 bytes is probably fine to return directly and it will
>> be enough for up to 128 features (+64 more comparing to the
>> mainline). OTOH, using pointers removes that "what if/when", so
>> it's more flexible in that term. So that's why I asked for other
>> folks' opinions -- 2 PoVs doesn't seem enough here.
> >From a quick grep it seems like the and() is mostly used in some form
> of:
>
> 	features = and(features, mask);
>
> and we already have netdev_features_clear() which modifies its first
> argument. I'd also have and() update its first arg rather than return
> the result as a value.
ok, I will follow the behaviour of bitmap_and().

> It will require changing the prototype of
> ndo_features_check() :( But yeah, I reckon we shouldn't be putting of
> refactoring, best if we make all the changes at once than have to
> revisit this once the flags grow again and return by value starts to
> be a problem.
> .
>



Thanks,
Jian