Hi Alan,
On Tue, Feb 25, 2020 at 02:39:23PM -0500, Alan Stern wrote:
> On Tue, 25 Feb 2020, Eugeniu Rosca wrote:
> > [1] (v5.6-rc3) git grep -En "[^=]\s+usb_autopm_get_interface\("
> > drivers/input/touchscreen/usbtouchscreen.c:1788: usb_autopm_get_interface(intf);
> > drivers/media/usb/stkwebcam/stk-webcam.c:628: usb_autopm_get_interface(dev->interface);
> > drivers/net/usb/hso.c:1308: usb_autopm_get_interface(serial->parent->interface);
> > drivers/net/usb/r8152.c:5231: usb_autopm_get_interface(tp->intf);
> > sound/usb/usx2y/us122l.c:192: usb_autopm_get_interface(iface);
>
> Your regular expression isn't right because it doesn't match lines
> where the usb_autopm_get_interface() is preceded only by one whitespace
> character (i.e., a tab). It also will match lines where there are two
> space characters between the = sign and the function name. I think
> what you want is more like "(^|[^=[:space:]])\s*" at the start of the
> RE.
Agreed. My version filters out some true positives.
>
> A revised search finds line 997 in drivers/usb/core/hub.c and lines
> 216, 269 in drivers/usb/core/port.c. (I didn't try looking in any
> other directories.) AFAICT all three of these should check the return
> value, although a error message in the kernel log probably isn't
> needed.
>
> Do you want to fix those instances up also, maybe merging them in with
> the existing patch?
I wonder if squashing all these fixes into one patch is the best option.
There are three commits fixed by the proposed changes in usb core:
- v5.6-rc3 commit 1208f9e1d758c9 ("USB: hub: Fix the broken detection of USB3 device in SMSC hub")
- v3.9-rc1 commit 971fcd492cebf5 ("usb: add runtime pm support for usb port device")
- v2.6.33-rc1 commit 253e05724f9230 ("USB: add a "remove hardware" sysfs attribute")
I assume a single fix will create some pain when applying it to the
stable branches. Do you have any preference/inputs about that?
--
Best Regards
Eugeniu Rosca
