| Message ID | 1604410265-30246-1-git-send-email-radhey.shyam.pandey@xilinx.com |
|---|---|
| State | New |
| Headers | show |
| Series | [net-next] net: emaclite: Add error handling for of_address_ and phy read functions | expand |
On Tue, Nov 03, 2020 at 07:01:05PM +0530, Radhey Shyam Pandey wrote: > From: Shravya Kumbham <shravya.kumbham@xilinx.com> > > Add ret variable, conditions to check the return value and it's error > path for of_address_to_resource() and phy_read() functions. > > Addresses-Coverity: Event check_return value. Hi Radhey This is well out of scope of a Coverity fix, but looking at the patch i noticed some bad things. > @@ -923,7 +929,7 @@ static int xemaclite_open(struct net_device *dev) > xemaclite_disable_interrupts(lp); > > if (lp->phy_node) { > - u32 bmcr; > + int bmcr; > > lp->phy_dev = of_phy_connect(lp->ndev, lp->phy_node, > xemaclite_adjust_link, 0, > @@ -945,6 +951,13 @@ static int xemaclite_open(struct net_device *dev) > > /* Restart auto negotiation */ > bmcr = phy_read(lp->phy_dev, MII_BMCR); > + if (bmcr < 0) { > + dev_err(&lp->ndev->dev, "phy_read failed\n"); > + phy_disconnect(lp->phy_dev); > + lp->phy_dev = NULL; > + > + return bmcr; > + } > bmcr |= (BMCR_ANENABLE | BMCR_ANRESTART); > phy_write(lp->phy_dev, MII_BMCR, bmcr); A MAC driver should not be touching the PHY. The call to phy_set_max_speed() should prevent the PHY from advertising 1G speeds, so there is no need to poke the advertise registers. And phy_start() will start auto-get if it is enabled. It would be nice if this code got cleaned up. Andrew
On Tue, 3 Nov 2020 19:01:05 +0530 Radhey Shyam Pandey wrote: > From: Shravya Kumbham <shravya.kumbham@xilinx.com> > > Add ret variable, conditions to check the return value and it's error > path for of_address_to_resource() and phy_read() functions. > > Addresses-Coverity: Event check_return value. > Signed-off-by: Shravya Kumbham <shravya.kumbham@xilinx.com> > Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com> Any reason not to apply this to net as a fix? > diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c > index 0c26f5b..fc5ccd1 100644 > --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c > +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c > @@ -820,7 +820,7 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg, > static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev) > { > struct mii_bus *bus; > - int rc; > + int rc, ret; > struct resource res; > struct device_node *np = of_get_parent(lp->phy_node); > struct device_node *npp; > @@ -834,7 +834,13 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev) > } > npp = of_get_parent(np); > > - of_address_to_resource(npp, 0, &res); > + ret = of_address_to_resource(npp, 0, &res); > + if (ret) { > + dev_err(dev, "%s resource error!\n", > + dev->of_node->full_name); > + of_node_put(lp->phy_node); I'm always confused by the of_* refcounting. Why do you need to put phy_node here, and nowhere else in this function? > + return ret; > + } > /* Restart auto negotiation */ > bmcr = phy_read(lp->phy_dev, MII_BMCR); > + if (bmcr < 0) { > + dev_err(&lp->ndev->dev, "phy_read failed\n"); > + phy_disconnect(lp->phy_dev); > + lp->phy_dev = NULL; > + > + return bmcr; > + } > bmcr |= (BMCR_ANENABLE | BMCR_ANRESTART); > phy_write(lp->phy_dev, MII_BMCR, bmcr); Does it really make much sense to validate the return value of phy_read() but not check any errors from phy_write()s?
> -----Original Message----- > From: Jakub Kicinski <kuba@kernel.org> > Sent: Sunday, November 8, 2020 1:05 AM > To: Radhey Shyam Pandey <radheys@xilinx.com> > Cc: davem@davemloft.net; Michal Simek <michals@xilinx.com>; > netdev@vger.kernel.org; linux-arm-kernel@lists.infradead.org; linux- > kernel@vger.kernel.org; git <git@xilinx.com>; Shravya Kumbham > <shravyak@xilinx.com> > Subject: Re: [PATCH net-next] net: emaclite: Add error handling for > of_address_ and phy read functions > > On Tue, 3 Nov 2020 19:01:05 +0530 Radhey Shyam Pandey wrote: > > From: Shravya Kumbham <shravya.kumbham@xilinx.com> > > > > Add ret variable, conditions to check the return value and it's error > > path for of_address_to_resource() and phy_read() functions. > > > > Addresses-Coverity: Event check_return value. > > Signed-off-by: Shravya Kumbham <shravya.kumbham@xilinx.com> > > Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com> > > Any reason not to apply this to net as a fix? Yes, it can be applied to net as a fix. > > > diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c > > b/drivers/net/ethernet/xilinx/xilinx_emaclite.c > > index 0c26f5b..fc5ccd1 100644 > > --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c > > +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c > > @@ -820,7 +820,7 @@ static int xemaclite_mdio_write(struct mii_bus > > *bus, int phy_id, int reg, static int xemaclite_mdio_setup(struct > > net_local *lp, struct device *dev) { > > struct mii_bus *bus; > > - int rc; > > + int rc, ret; > > struct resource res; > > struct device_node *np = of_get_parent(lp->phy_node); > > struct device_node *npp; > > @@ -834,7 +834,13 @@ static int xemaclite_mdio_setup(struct net_local > *lp, struct device *dev) > > } > > npp = of_get_parent(np); > > > > - of_address_to_resource(npp, 0, &res); > > + ret = of_address_to_resource(npp, 0, &res); > > + if (ret) { > > + dev_err(dev, "%s resource error!\n", > > + dev->of_node->full_name); > > + of_node_put(lp->phy_node); > > I'm always confused by the of_* refcounting. Why do you need to put > phy_node here, and nowhere else in this function? Initially, we added of_node_put(phy_node) thinking about this particular coverity change. But agree it has to be added for all error path i.e better place would be in xemaclite_of_probe() error label. > > > + return ret; > > + } > > > /* Restart auto negotiation */ > > bmcr = phy_read(lp->phy_dev, MII_BMCR); > > + if (bmcr < 0) { > > + dev_err(&lp->ndev->dev, "phy_read failed\n"); > > + phy_disconnect(lp->phy_dev); > > + lp->phy_dev = NULL; > > + > > + return bmcr; > > + } > > bmcr |= (BMCR_ANENABLE | BMCR_ANRESTART); > > phy_write(lp->phy_dev, MII_BMCR, bmcr); > > Does it really make much sense to validate the return value of > phy_read() but not check any errors from phy_write()s? Error handling was added for phy_read as it was using return value and reported by coverity. But yes we in a follow-up patch we can extend error handling for phy_write as well.
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index 0c26f5b..fc5ccd1 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -820,7 +820,7 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg, static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev) { struct mii_bus *bus; - int rc; + int rc, ret; struct resource res; struct device_node *np = of_get_parent(lp->phy_node); struct device_node *npp; @@ -834,7 +834,13 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev) } npp = of_get_parent(np); - of_address_to_resource(npp, 0, &res); + ret = of_address_to_resource(npp, 0, &res); + if (ret) { + dev_err(dev, "%s resource error!\n", + dev->of_node->full_name); + of_node_put(lp->phy_node); + return ret; + } if (lp->ndev->mem_start != res.start) { struct phy_device *phydev; phydev = of_phy_find_device(lp->phy_node); @@ -923,7 +929,7 @@ static int xemaclite_open(struct net_device *dev) xemaclite_disable_interrupts(lp); if (lp->phy_node) { - u32 bmcr; + int bmcr; lp->phy_dev = of_phy_connect(lp->ndev, lp->phy_node, xemaclite_adjust_link, 0, @@ -945,6 +951,13 @@ static int xemaclite_open(struct net_device *dev) /* Restart auto negotiation */ bmcr = phy_read(lp->phy_dev, MII_BMCR); + if (bmcr < 0) { + dev_err(&lp->ndev->dev, "phy_read failed\n"); + phy_disconnect(lp->phy_dev); + lp->phy_dev = NULL; + + return bmcr; + } bmcr |= (BMCR_ANENABLE | BMCR_ANRESTART); phy_write(lp->phy_dev, MII_BMCR, bmcr);