netdev - Re: [PATCH net 0/2] net: macb: fix probing of PHY not described in the dt

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date:   Thu, 19 Dec 2019 17:32:39 -0800 (PST)
From:   David Miller <davem@...emloft.net>
To:     antoine.tenart@...tlin.com
Cc:     andrew@...n.ch, f.fainelli@...il.com, hkallweit1@...il.com,
        alexandre.belloni@...tlin.com, nicolas.ferre@...rochip.com,
        netdev@...r.kernel.org, thomas.petazzoni@...tlin.com
Subject: Re: [PATCH net 0/2] net: macb: fix probing of PHY not described in
 the dt

From: Antoine Tenart <antoine.tenart@...tlin.com>
Date: Tue, 17 Dec 2019 18:07:40 +0100

> The macb Ethernet driver supports various ways of referencing its
> network PHY. When a device tree is used the PHY can be referenced with
> a phy-handle or, if connected to its internal MDIO bus, described in
> a child node. Some platforms omitted the PHY description while
> connecting the PHY to the internal MDIO bus and in such cases the MDIO
> bus has to be scanned "manually" by the macb driver.
> 
> Prior to the phylink conversion the driver registered the MDIO bus with
> of_mdiobus_register and then in case the PHY couldn't be retrieved
> using dt or using phy_find_first (because registering an MDIO bus with
> of_mdiobus_register masks all PHYs) the macb driver was "manually"
> scanning the MDIO bus (like mdiobus_register does). The phylink
> conversion did break this particular case but reimplementing the manual
> scan of the bus in the macb driver wouldn't be very clean. The solution
> seems to be registering the MDIO bus based on if the PHYs are described
> in the device tree or not.
> 
> There are multiple ways to do this, none is perfect. I chose to check if
> any of the child nodes of the macb node was a network PHY and based on
> this to register the MDIO bus with the of_ helper or not. The drawback
> is boards referencing the PHY through phy-handle, would scan the entire
> MDIO bus of the macb at boot time (as the MDIO bus would be registered
> with mdiobus_register). For this solution to work properly
> of_mdiobus_child_is_phy has to be exported, which means the patch doing
> so has to be backported to -stable as well.
> 
> Another possible solution could have been to simply check if the macb
> node has a child node by counting its sub-nodes. This isn't techically
> perfect, as there could be other sub-nodes (in practice this should be
> fine, fixed-link being taken care of in the driver). We could also
> simply s/of_mdiobus_register/mdiobus_register/ but that could break
> boards using the PHY description in child node as a selector (which
> really would be not a proper way to do this...).
> 
> The real issue here being having PHYs not described in the dt but we
> have dt backward compatibility, so we have to live with that.

Series applied, thanks Antoine.