| Message ID | 20200126194950.31699-1-olteanv@gmail.com |
|---|---|
| State | Not Applicable |
| Delegated to: | David Miller |
| Headers | show |
| Series | ARM: dts: ls1021a: Restore MDIO compatible to gianfar | expand |
On Sun, Jan 26, 2020 at 09:49:50PM +0200, Vladimir Oltean wrote: > The difference between "fsl,etsec2-mdio" and "gianfar" has to do with > the .get_tbipa function, which calculates the address of the TBIPA > register automatically, if not explicitly specified. [ see > drivers/net/ethernet/freescale/fsl_pq_mdio.c ]. On LS1021A, the TBIPA > register is at offset 0x30 within the port register block, which is what > the "gianfar" method of calculating addresses actually does. > > Luckily, the bad "compatible" is inconsequential for ls1021a.dtsi, > because the TBIPA register is explicitly specified via the second "reg" > (<0x0 0x2d10030 0x0 0x4>), so the "get_tbipa" function is dead code. > Nonetheless it's good to restore it to its correct value. > > Background discussion: > https://www.spinics.net/lists/stable/msg361156.html > > Fixes: c7861adbe37f ("ARM: dts: ls1021: Fix SGMII PCS link remaining down after PHY disconnect") > Reported-by: Pavel Machek <pavel@denx.de> > Signed-off-by: Vladimir Oltean <olteanv@gmail.com> Applied, thanks.
diff --git a/arch/arm/boot/dts/ls1021a.dtsi b/arch/arm/boot/dts/ls1021a.dtsi index 2f6977ada447..63d9f4a066e3 100644 --- a/arch/arm/boot/dts/ls1021a.dtsi +++ b/arch/arm/boot/dts/ls1021a.dtsi @@ -728,7 +728,7 @@ }; mdio0: mdio@2d24000 { - compatible = "fsl,etsec2-mdio"; + compatible = "gianfar"; device_type = "mdio"; #address-cells = <1>; #size-cells = <0>; @@ -737,7 +737,7 @@ }; mdio1: mdio@2d64000 { - compatible = "fsl,etsec2-mdio"; + compatible = "gianfar"; device_type = "mdio"; #address-cells = <1>; #size-cells = <0>;
The difference between "fsl,etsec2-mdio" and "gianfar" has to do with the .get_tbipa function, which calculates the address of the TBIPA register automatically, if not explicitly specified. [ see drivers/net/ethernet/freescale/fsl_pq_mdio.c ]. On LS1021A, the TBIPA register is at offset 0x30 within the port register block, which is what the "gianfar" method of calculating addresses actually does. Luckily, the bad "compatible" is inconsequential for ls1021a.dtsi, because the TBIPA register is explicitly specified via the second "reg" (<0x0 0x2d10030 0x0 0x4>), so the "get_tbipa" function is dead code. Nonetheless it's good to restore it to its correct value. Background discussion: https://www.spinics.net/lists/stable/msg361156.html Fixes: c7861adbe37f ("ARM: dts: ls1021: Fix SGMII PCS link remaining down after PHY disconnect") Reported-by: Pavel Machek <pavel@denx.de> Signed-off-by: Vladimir Oltean <olteanv@gmail.com> --- arch/arm/boot/dts/ls1021a.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)