| Message ID | 20221201175525.2733125-2-l.stach@pengutronix.de (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | [1/2] net: asix: Simplify return value check after asix_check_host_enable | expand |
On Thu, Dec 01, 2022 at 06:55:25PM +0100, Lucas Stach wrote: > We've seen device access fail with -EPROTO when the device has been > recently disconnected and before the USB core had a chance to handle > the disconnect hub event. It doesn't make sense to continue on trying > to enable host access when the adapter is gone. > > Signed-off-by: Lucas Stach <l.stach@pengutronix.de> > --- > drivers/net/usb/asix_common.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c > index be1e103b7a95..28b31e4da020 100644 > --- a/drivers/net/usb/asix_common.c > +++ b/drivers/net/usb/asix_common.c > @@ -96,7 +96,7 @@ static int asix_check_host_enable(struct usbnet *dev, int in_pm) > > for (i = 0; i < AX_HOST_EN_RETRIES; ++i) { > ret = asix_set_sw_mii(dev, in_pm); > - if (ret == -ENODEV || ret == -ETIMEDOUT) > + if (ret == -ENODEV || ret == -ETIMEDOUT || ret == -EPROTO) It looks like you can put if (ret < 0) here, > break; > usleep_range(1000, 1100); > ret = asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG, > -- > 2.30.2 >
On Sun, 4 Dec 2022 13:48:07 +0200 Leon Romanovsky wrote: > On Thu, Dec 01, 2022 at 06:55:25PM +0100, Lucas Stach wrote: > > We've seen device access fail with -EPROTO when the device has been > > recently disconnected and before the USB core had a chance to handle > > the disconnect hub event. It doesn't make sense to continue on trying > > to enable host access when the adapter is gone. > > > > Signed-off-by: Lucas Stach <l.stach@pengutronix.de> > > --- > > drivers/net/usb/asix_common.c | 2 +- > > 1 file changed, 1 insertion(+), 1 deletion(-) > > > > diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c > > index be1e103b7a95..28b31e4da020 100644 > > --- a/drivers/net/usb/asix_common.c > > +++ b/drivers/net/usb/asix_common.c > > @@ -96,7 +96,7 @@ static int asix_check_host_enable(struct usbnet *dev, int in_pm) > > > > for (i = 0; i < AX_HOST_EN_RETRIES; ++i) { > > ret = asix_set_sw_mii(dev, in_pm); > > - if (ret == -ENODEV || ret == -ETIMEDOUT) > > + if (ret == -ENODEV || ret == -ETIMEDOUT || ret == -EPROTO) > > It looks like you can put if (ret < 0) here, Right, or we need a clarification in the commit message why it's okay to continue for other errors (and continue as if the error didn't happen, not just retry).
diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index be1e103b7a95..28b31e4da020 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -96,7 +96,7 @@ static int asix_check_host_enable(struct usbnet *dev, int in_pm) for (i = 0; i < AX_HOST_EN_RETRIES; ++i) { ret = asix_set_sw_mii(dev, in_pm); - if (ret == -ENODEV || ret == -ETIMEDOUT) + if (ret == -ENODEV || ret == -ETIMEDOUT || ret == -EPROTO) break; usleep_range(1000, 1100); ret = asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG,
We've seen device access fail with -EPROTO when the device has been recently disconnected and before the USB core had a chance to handle the disconnect hub event. It doesn't make sense to continue on trying to enable host access when the adapter is gone. Signed-off-by: Lucas Stach <l.stach@pengutronix.de> --- drivers/net/usb/asix_common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)