6.7-stable review patch. If anyone has any objections, please let me know.
------------------
From: Andrew Lunn andrew@lunn.ch
commit 585b40e25dc9ff3d2b03d1495150540849009e5b upstream.
Not all mv88e6xxx device support C45 read/write operations. Those which do not return -EOPNOTSUPP. However, when phylib scans the bus, it considers this fatal, and the probe of the MDIO bus fails, which in term causes the mv88e6xxx probe as a whole to fail.
When there is no device on the bus for a given address, the pull up resistor on the data line results in the read returning 0xffff. The phylib core code understands this when scanning for devices on the bus. C45 allows multiple devices to be supported at one address, so phylib will perform a few reads at each address, so although thought not the most efficient solution, it is a way to avoid fatal errors. Make use of this as a minimal fix for stable to fix the probing problems.
Follow up patches will rework how C45 operates to make it similar to C22 which considers -ENODEV as a none-fatal, and swap mv88e6xxx to using this.
Cc: stable@vger.kernel.org Fixes: 743a19e38d02 ("net: dsa: mv88e6xxx: Separate C22 and C45 transactions") Reported-by: Tim Menninger tmenninger@purestorage.com Signed-off-by: Andrew Lunn andrew@lunn.ch Link: https://lore.kernel.org/r/20240129224948.1531452-1-andrew@lunn.ch Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/dsa/mv88e6xxx/chip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
--- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3545,7 +3545,7 @@ static int mv88e6xxx_mdio_read_c45(struc int err;
if (!chip->info->ops->phy_read_c45) - return -EOPNOTSUPP; + return 0xffff;
mv88e6xxx_reg_lock(chip); err = chip->info->ops->phy_read_c45(chip, bus, phy, devad, reg, &val);