| Message ID | AM9PR04MB85062E3A66BA92EF8D996513E2832@AM9PR04MB8506.eurprd04.prod.outlook.com |
|---|---|
| State | New |
| Headers | show |
| Series | [v2,1/7] net: driver: stmmac: extend CSR calc support | expand |
On Sun, Aug 18, 2024 at 09:50:46PM +0000, Jan Petrous (OSS) wrote: > The helper rgmii_clock() implemented Russel's hint during stmmac > glue driver review: > > --- > We seem to have multiple cases of very similar logic in lots of stmmac > platform drivers, and I think it's about time we said no more to this. > So, what I think we should do is as follows: > > add the following helper - either in stmmac, or more generically > (phylib? - in which case its name will need changing.) > > static long stmmac_get_rgmii_clock(int speed) > { > switch (speed) { > case SPEED_10: > return 2500000; > > case SPEED_100: > return 25000000; > > case SPEED_1000: > return 125000000; > > default: > return -ENVAL; > } > } > > Then, this can become: > > long tx_clk_rate; > > ... > > tx_clk_rate = stmmac_get_rgmii_clock(speed); > if (tx_clk_rate < 0) { > dev_err(gmac->dev, "Unsupported/Invalid speed: %d\n", speed); > return; > } > > ret = clk_set_rate(gmac->tx_clk, tx_clk_rate); > --- > > Signed-off-by: Jan Petrous (OSS) <jan.petrous@oss.nxp.com> > --- > include/linux/phy.h | 21 +++++++++++++++++++++ > 1 file changed, 21 insertions(+) > > diff --git a/include/linux/phy.h b/include/linux/phy.h > index 6b7d40d49129..bb797364d91c 100644 > --- a/include/linux/phy.h > +++ b/include/linux/phy.h > @@ -298,6 +298,27 @@ static inline const char *phy_modes(phy_interface_t interface) > } > } > > +/** > + * rgmi_clock - map link speed to the clock rate nit: rgmii_clock Flagged by ./scripts/kernel-doc -none > + * @speed: link speed value > + * > + * Description: maps RGMII supported link speeds > + * into the clock rates. > + */ > +static inline long rgmii_clock(int speed) > +{ > + switch (speed) { > + case SPEED_10: > + return 2500000; > + case SPEED_100: > + return 25000000; > + case SPEED_1000: > + return 125000000; > + default: > + return -EINVAL; > + } > +} > + > #define PHY_INIT_TIMEOUT 100000 > #define PHY_FORCE_TIMEOUT 10 > > -- > 2.46.0 > >
On Sun, Aug 18, 2024 at 09:50:46PM +0000, Jan Petrous (OSS) wrote: > The helper rgmii_clock() implemented Russel's hint during stmmac > glue driver review: > > --- > We seem to have multiple cases of very similar logic in lots of stmmac > platform drivers, and I think it's about time we said no more to this. > So, what I think we should do is as follows: > > add the following helper - either in stmmac, or more generically > (phylib? - in which case its name will need changing.) > > static long stmmac_get_rgmii_clock(int speed) > { > switch (speed) { > case SPEED_10: > return 2500000; > > case SPEED_100: > return 25000000; > > case SPEED_1000: > return 125000000; > > default: > return -ENVAL; > } > } > > Then, this can become: > > long tx_clk_rate; > > ... > > tx_clk_rate = stmmac_get_rgmii_clock(speed); > if (tx_clk_rate < 0) { > dev_err(gmac->dev, "Unsupported/Invalid speed: %d\n", speed); > return; > } > > ret = clk_set_rate(gmac->tx_clk, tx_clk_rate); > --- > > Signed-off-by: Jan Petrous (OSS) <jan.petrous@oss.nxp.com> This Signed-off-by: needs to be above the first ---, otherwise it gets discard. When you repost, please do try to get threading correct. Andrew --- pw-bot: cr
On Sun, Aug 18, 2024 at 09:50:46PM +0000, Jan Petrous (OSS) wrote: > The helper rgmii_clock() implemented Russel's hint during stmmac > glue driver review: > > --- > We seem to have multiple cases of very similar logic in lots of stmmac > platform drivers, and I think it's about time we said no more to this. > So, what I think we should do is as follows: > > add the following helper - either in stmmac, or more generically > (phylib? - in which case its name will need changing.) As Russell pointed out, this code appears a few times in the stmmac driver. Please include patches changing the other instances to use this helper. It also looks like macb, and maybe xgene_enet_hw.c could use it as well. Andrew
diff --git a/include/linux/phy.h b/include/linux/phy.h index 6b7d40d49129..bb797364d91c 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -298,6 +298,27 @@ static inline const char *phy_modes(phy_interface_t interface) } } +/** + * rgmi_clock - map link speed to the clock rate + * @speed: link speed value + * + * Description: maps RGMII supported link speeds + * into the clock rates. + */ +static inline long rgmii_clock(int speed) +{ + switch (speed) { + case SPEED_10: + return 2500000; + case SPEED_100: + return 25000000; + case SPEED_1000: + return 125000000; + default: + return -EINVAL; + } +} + #define PHY_INIT_TIMEOUT 100000 #define PHY_FORCE_TIMEOUT 10
The helper rgmii_clock() implemented Russel's hint during stmmac glue driver review: --- We seem to have multiple cases of very similar logic in lots of stmmac platform drivers, and I think it's about time we said no more to this. So, what I think we should do is as follows: add the following helper - either in stmmac, or more generically (phylib? - in which case its name will need changing.) static long stmmac_get_rgmii_clock(int speed) { switch (speed) { case SPEED_10: return 2500000; case SPEED_100: return 25000000; case SPEED_1000: return 125000000; default: return -ENVAL; } } Then, this can become: long tx_clk_rate; ... tx_clk_rate = stmmac_get_rgmii_clock(speed); if (tx_clk_rate < 0) { dev_err(gmac->dev, "Unsupported/Invalid speed: %d\n", speed); return; } ret = clk_set_rate(gmac->tx_clk, tx_clk_rate); --- Signed-off-by: Jan Petrous (OSS) <jan.petrous@oss.nxp.com> --- include/linux/phy.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+)