[00/12] Rework PHY reset handling

The current phy reset handling is broken in a way that it needs
pre-running firmware to setup the phy initially. Since the very first
step is to readout the PHYID1/2 registers before doing anything else.

The whole dection logic will fall apart if the pre-running firmware
don't setup the phy accordingly or the kernel boot resets GPIOs states
or disables clocks. In such cases the PHYID1/2 read access will fail and
so the whole detection will fail.

I fixed this via this series, the fix will include a new kernel API
called phy_device_atomic_register() which will do all necessary things
and return a 'struct phy_device' on success. So setting up a phy and the
phy state machine is more convenient.

I tested the series on a i.MX8MP-EVK and a custom board which have a
TJA1102 dual-port ethernet phy. Other testers are welcome :)

Regards,
  Marco

Signed-off-by: Marco Felsch <m.felsch@pengutronix.de>
---
Marco Felsch (12):
      net: phy: refactor phy_device_create function
      net: phy: refactor get_phy_device function
      net: phy: add phy_device_set_miits helper
      net: phy: unify get_phy_device and phy_device_create parameter list
      net: phy: add phy_id_broken support
      net: phy: add phy_device_atomic_register helper
      net: mdio: make use of phy_device_atomic_register helper
      net: phy: add possibility to specify mdio device parent
      net: phy: nxp-tja11xx: make use of phy_device_atomic_register()
      of: mdio: remove now unused of_mdiobus_phy_device_register()
      net: mdiobus: remove now unused fwnode helpers
      net: phy: add default gpio assert/deassert delay

 Documentation/firmware-guide/acpi/dsd/phy.rst     |   2 +-
 MAINTAINERS                                       |   1 -
 drivers/net/ethernet/adi/adin1110.c               |   6 +-
 drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c       |   8 +-
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c |  11 +-
 drivers/net/ethernet/socionext/netsec.c           |   7 +-
 drivers/net/mdio/Kconfig                          |   7 -
 drivers/net/mdio/Makefile                         |   1 -
 drivers/net/mdio/acpi_mdio.c                      |  20 +-
 drivers/net/mdio/fwnode_mdio.c                    | 183 ------------
 drivers/net/mdio/mdio-xgene.c                     |   6 +-
 drivers/net/mdio/of_mdio.c                        |  23 +-
 drivers/net/phy/bcm-phy-ptp.c                     |   2 +-
 drivers/net/phy/dp83640.c                         |   2 +-
 drivers/net/phy/fixed_phy.c                       |   6 +-
 drivers/net/phy/mdio_bus.c                        |   7 +-
 drivers/net/phy/micrel.c                          |   2 +-
 drivers/net/phy/mscc/mscc_ptp.c                   |   2 +-
 drivers/net/phy/nxp-c45-tja11xx.c                 |   2 +-
 drivers/net/phy/nxp-tja11xx.c                     |  47 ++-
 drivers/net/phy/phy_device.c                      | 348 +++++++++++++++++++---
 drivers/net/phy/sfp.c                             |   7 +-
 include/linux/fwnode_mdio.h                       |  35 ---
 include/linux/of_mdio.h                           |   8 -
 include/linux/phy.h                               |  46 ++-
 25 files changed, 442 insertions(+), 347 deletions(-)
---
base-commit: 054fbf7ff8143d35ca7d3bb5414bb44ee1574194
change-id: 20230405-net-next-topic-net-phy-reset-4f79ff7df4a0

Best regards,

Lets try again....

There are a number of things i don't like about this patchset.

It does too many different things.

It pulls workarounds into the core.

I don't like the phy_device_config. It would make sense if there were
more than 6 arguments to pass to a function, but not for less.

I don't like the name phy_device_atomic_register(), but that is bike
shedding.

There is no really strong argument to change the API.

There is no really strong argument to move to fwnode.

The problem you are trying to solve is to call phy_device_reset()
earlier, before reading the ID registers. Please produce a patchset
which is only focused on that. Nothing else.

      Andrew