Re: [PATCH v3 1/3] usb: core: hub: fix unhandled return by employing a void function

[Alan Stern]

On Wed, 26 Feb 2020, Eugeniu Rosca wrote:

> Address below Coverity complaint (Feb 25, 2020, 8:06 AM CET):
> 
> *** CID 1458999:  Error handling issues  (CHECKED_RETURN)
> /drivers/usb/core/hub.c: 1869 in hub_probe()
> 1863
> 1864            if (id->driver_info & HUB_QUIRK_CHECK_PORT_AUTOSUSPEND)
> 1865                    hub->quirk_check_port_auto_suspend = 1;
> 1866
> 1867            if (id->driver_info & HUB_QUIRK_DISABLE_AUTOSUSPEND) {
> 1868                    hub->quirk_disable_autosuspend = 1;
>  >>>     CID 1458999:  Error handling issues  (CHECKED_RETURN)
>  >>>     Calling "usb_autopm_get_interface" without checking return value (as is done elsewhere 97 out of 111 times).
> 1869                    usb_autopm_get_interface(intf);
> 1870            }
> 1871
> 1872            if (hub_configure(hub, &desc->endpoint[0].desc) >= 0)
> 1873                    return 0;
> 1874
> 
> Rather than checking the return value of 'usb_autopm_get_interface()',
> switch to the usb_autopm_get_interface_no_resume() API, as per:
> 
> On Tue, Feb 25, 2020 at 10:32:32AM -0500, Alan Stern wrote:
>  ------ 8< ------
>  > This change (i.e. 'ret = usb_autopm_get_interface') is not necessary,
>  > because the resume operation cannot fail at this point (interfaces
>  > are always powered-up during probe). A better solution would be to
>  > call usb_autopm_get_interface_no_resume() instead.
>  ------ 8< ------
> 
> Fixes: 1208f9e1d758c9 ("USB: hub: Fix the broken detection of USB3 device in SMSC hub")
> Cc: Hardik Gajjar <hgajjar@xxxxxxxxxxxxxx>
> Cc: Alan Stern <stern@xxxxxxxxxxxxxxxxxxx>
> Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
> Cc: stable@xxxxxxxxxxxxxxx # v4.14+
> Reported-by: scan-admin@xxxxxxxxxxxx
> Suggested-by: Alan Stern <stern@xxxxxxxxxxxxxxxxxxx>
> Signed-off-by: Eugeniu Rosca <erosca@xxxxxxxxxxxxxx>

For all three patches:

Acked-by: Alan Stern <stern@xxxxxxxxxxxxxxxxxxx>