Re: [PATCH net-next] net: dsa: mv88e6xxx: Fill in STU support for all supported chips

[Marek Behún]

On Sat, 19 Mar 2022 12:03:45 +0100
Tobias Waldekranz <tobias@xxxxxxxxxxxxxx> wrote:

> Some chips using the split VTU/STU design will not accept VTU entries
> who's SID points to an invalid STU entry. Therefore, mark all those
> chips with either the mv88e6352_g1_stu_* or mv88e6390_g1_stu_* ops as
> appropriate.
> 
> Notably, chips for the Opal Plus (6085/6097) era seem to use a
> different implementation than those from Agate (6352) and onwards,
> even though their external interface is the same. The former happily
> accepts VTU entries referencing invalid STU entries, while the latter
> does not.
> 
> This fixes an issue where the driver would fail to probe switch trees
> that contained chips of the Agate/Topaz generation which did not
> declare STU support, as loaded VTU entries would be read back as
> invalid.
> 
> Fixes: 49c98c1dc7d9 ("net: dsa: mv88e6xxx: Disentangle STU from VTU")
> Reported-by: Marek Behún <kabel@xxxxxxxxxx>
> Signed-off-by: Tobias Waldekranz <tobias@xxxxxxxxxxxxxx>

Tested-by: Marek Behún <kabel@xxxxxxxxxx>