Messages in this thread | | | Date | Sat, 19 Mar 2022 20:00:41 +0100 | From | Marek Behún <> | Subject | Re: [PATCH net-next] net: dsa: mv88e6xxx: Fill in STU support for all supported chips |
| |
On Sat, 19 Mar 2022 12:03:45 +0100 Tobias Waldekranz <tobias@waldekranz.com> 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@kernel.org> > Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com>
Tested-by: Marek Behún <kabel@kernel.org>
| |