Hi Andrew, On Sat, Jan 20, 2024 at 08:21:25PM +0100, Andrew Lunn wrote: > 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, and a number of MDIO bus masters make use of this as a way to > indicate they cannot perform the read. > > Make us of this as a minimal fix for stable where the mv88e6xxx s/us/use/ Also, what is the "proper" fix if this is the minimal one for stable? > returns EOPNOTSUPP when the hardware does not support C45, but phylib > interprets this as a fatal error, which it should not be. I think the commit message is a bit backwards, it starts with an explanation of the solution without ever clarifying exactly what is the problem. At least it could have referenced the old thread which explains that: https://lore.kernel.org/netdev/CAO-L_44YVi0HDk4gC9QijMZrYNGoKtfH7qsXOwtDwM4VrFRDHw@xxxxxxxxxxxxxx/ > > Cc: stable@xxxxxxxxxxxxxxx > Reported-by: Tim Menninger <tmenninger@xxxxxxxxxxxxxxx> > Fixes: 1a136ca2e089 ("net: mdio: scan bus based on bus capabilities for C22 and C45") > Fixes: da099a7fb13d ("net: phy: Remove probe_capabilities") > Signed-off-by: Andrew Lunn <andrew@xxxxxxx> > --- > drivers/net/dsa/mv88e6xxx/chip.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c > index 383b3c4d6f59..614cabb5c1b0 100644 > --- a/drivers/net/dsa/mv88e6xxx/chip.c > +++ b/drivers/net/dsa/mv88e6xxx/chip.c > @@ -3659,7 +3659,7 @@ static int mv88e6xxx_mdio_read_c45(struct mii_bus *bus, int phy, int devad, > 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); > -- > 2.43.0 > Is this an RFC pending testing from Tim? Or have you reproduced the problem and confirmed that this fixes it? It's not clear how the old thread ended.
