On 06/12/2023 16:27, Michal Koutný wrote:
> These modules may be loaded lazily without user's awareness and
> control. Add respective aliases to modules and request them under these
> aliases so that modprobe's blacklisting mechanism (through aliases)
> works for them. (The same pattern exists e.g. for filesystem
> modules.)
>
> Original module names remain unchanged.
>
Can't you just keep the sch-, cls-, act- prefixes for the aliases?
They look odd in the current patchset TBH
On Wed, Dec 06, 2023 at 05:16:28PM -0300, Pedro Tammela <[email protected]> wrote:
> Can't you just keep the sch-, cls-, act- prefixes for the aliases?
> They look odd in the current patchset TBH
I'm open to different better naming.
Although, this natural option would clash with the behavior
(modprobe(8)):
> there is no difference between _ and - in module names
Thus blacklisting via an alias vs not-blacklisting via non-canonical
name would contradict each other :-/
Michal
On Wed, 6 Dec 2023 22:18:25 +0100
Michal Koutný <[email protected]> wrote:
> On Wed, Dec 06, 2023 at 05:16:28PM -0300, Pedro Tammela <[email protected]> wrote:
> > Can't you just keep the sch-, cls-, act- prefixes for the aliases?
> > They look odd in the current patchset TBH
>
> I'm open to different better naming.
>
> Although, this natural option would clash with the behavior
> (modprobe(8)):
>
> > there is no difference between _ and - in module names
>
> Thus blacklisting via an alias vs not-blacklisting via non-canonical
> name would contradict each other :-/
>
> Michal
It is not clear to me what this patchset is trying to fix.
Autoloading happens now, but it does depend on the name not alias.
On Wed, Dec 06, 2023 at 02:28:57PM -0800, Stephen Hemminger <[email protected]> wrote:
> It is not clear to me what this patchset is trying to fix.
> Autoloading happens now, but it does depend on the name not alias.
There are some more details in the thread of v1 [1] [2].
Does it clarify?
Thanks,
Michal
[1] https://lore.kernel.org/r/yerqczxbz6qlrslkfbu6u2emb5esqe7tkrexdbneite2ah2a6i@l6arp7nzyj75/
[2] Oh, I realize I forgot to add v2 to today's posting.
Michal Koutný <[email protected]> writes:
> On Wed, Dec 06, 2023 at 02:28:57PM -0800, Stephen Hemminger <[email protected]> wrote:
>> It is not clear to me what this patchset is trying to fix.
>> Autoloading happens now, but it does depend on the name not alias.
>
> There are some more details in the thread of v1 [1] [2].
> Does it clarify?
Yes, but this should be explained clearly in the commit message
(including the reason why this is useful, in the follow-up to [1]).
-Toke
On Wed, 6 Dec 2023 23:49:14 +0100
Michal Koutný <[email protected]> wrote:
> On Wed, Dec 06, 2023 at 02:28:57PM -0800, Stephen Hemminger <[email protected]> wrote:
> > It is not clear to me what this patchset is trying to fix.
> > Autoloading happens now, but it does depend on the name not alias.
>
> There are some more details in the thread of v1 [1] [2].
> Does it clarify?
>
> Thanks,
> Michal
>
> [1] https://lore.kernel.org/r/yerqczxbz6qlrslkfbu6u2emb5esqe7tkrexdbneite2ah2a6i@l6arp7nzyj75/
> [2] Oh, I realize I forgot to add v2 to today's posting.
>
>
So your using blacklist as workaround security method and the name confuses it now.