These 6 patch is a first attempt at reducting qca8k_priv space.
The code changed a lot during times and we have many old logic
that can be replaced with new implementation

The first patch drop the tracking of MTU. We mimic what was done
for mtk and we change MTU only when CPU port is changed.

The second patch finally drop a piece of story of this driver.
The ar8xxx_port_status struct was used by the first implementation
of this driver to put all sort of status data for the port...
With the evolution of DSA all that stuff got dropped till only
the enabled state was the only part of the that struct.
Since it's overkill to keep an array of int, we convert the variable
to a simple u8 where we store the status of each port. This is needed
to don't reanable ports on system resume.

The third patch is a preparation for patch 4. As Vladimir explained
in another patch, we waste a tons of space by keeping a duplicate of
the switch dsa ops in qca8k_priv. The only reason for this is to
dynamically set the correct mdiobus configuration (a legacy dsa one,
or a custom dedicated one)
To solve this problem, we just drop the phy_read/phy_write and we
declare a custom mdiobus in any case. 
This way we can use a static dsa switch ops struct and we can drop it
from qca8k_priv

Patch 4 drop the duplicated dsa_switch_ops.

Patch 5 is a fixup for mdio read error.

Patch 6 is an effort to standardize how bus name are done.

This series is just a start of more cleanup.

The idea is to move this driver to the qca dir and split common code
from specific code. Also the mgmt eth code still requires some love
and can totally be optimized by recycling the same skb over time.

Also while working on the MTU it was notice some problem with
the stmmac driver and with the reloading phase that cause all
sort of problems with qca8k.

I'm sending this here just to try to keep small series instead of
proposing monster series hard to review.

v2:
- Rework MTU patch
v3:
- Drop unrealated changes from patch 3
- Add fixup patch for mdio read
- Unify bus name for legacy and OF mdio bus

*** BLURB HERE ***

Ansuel Smith (6):
  net: dsa: qca8k: drop MTU tracking from qca8k_priv
  net: dsa: qca8k: drop port_sts from qca8k_priv
  net: dsa: qca8k: rework and simplify mdiobus logic
  net: dsa: qca8k: drop dsa_switch_ops from qca8k_priv
  net: dsa: qca8k: correctly handle mdio read error
  net: dsa: qca8k: unify bus id naming with legacy and OF mdio bus

 drivers/net/dsa/qca8k.c | 145 +++++++++++++++-------------------------
 drivers/net/dsa/qca8k.h |  12 ++--
 2 files changed, 57 insertions(+), 100 deletions(-)

-- 
2.34.1

Hello:

This series was applied to netdev/net-next.git (master)
by David S. Miller <davem@davemloft.net>:

On Sat, 16 Apr 2022 01:30:11 +0200 you wrote:
> These 6 patch is a first attempt at reducting qca8k_priv space.
> The code changed a lot during times and we have many old logic
> that can be replaced with new implementation
> 
> The first patch drop the tracking of MTU. We mimic what was done
> for mtk and we change MTU only when CPU port is changed.
> 
> [...]

Here is the summary with links:
  - [net-next,v3,1/6] net: dsa: qca8k: drop MTU tracking from qca8k_priv
    https://git.kernel.org/netdev/net-next/c/69fd055957a0
  - [net-next,v3,2/6] net: dsa: qca8k: drop port_sts from qca8k_priv
    https://git.kernel.org/netdev/net-next/c/2b8fd87af7f1
  - [net-next,v3,3/6] net: dsa: qca8k: rework and simplify mdiobus logic
    https://git.kernel.org/netdev/net-next/c/8255212e4130
  - [net-next,v3,4/6] net: dsa: qca8k: drop dsa_switch_ops from qca8k_priv
    https://git.kernel.org/netdev/net-next/c/2349b83a2486
  - [net-next,v3,5/6] net: dsa: qca8k: correctly handle mdio read error
    https://git.kernel.org/netdev/net-next/c/6cfc03b60220
  - [net-next,v3,6/6] net: dsa: qca8k: unify bus id naming with legacy and OF mdio bus
    https://git.kernel.org/netdev/net-next/c/8d1af50842bf

You are awesome, thank you!
-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html