Messages in this thread | | | Subject | Re: [PATCH] staging: comedi: usbduxfast: Improve unlocking of a mutex in usbduxfast_ai_insn_read() | From | SF Markus Elfring <> | Date | Fri, 3 Nov 2017 17:39:21 +0100 |
| |
>> @@ -838,6 +834,10 @@ static int usbduxfast_ai_insn_read(struct comedi_device *dev, >> mutex_unlock(&devpriv->mut); >> return insn->n; > > Minor niggle: You could also remove that call to mutex_unlock() by replacing the above three lines with: > > ret = insn->n; > > which will fall through to the 'unlock:' label below.
Thanks for your suggestion.
Such a software refactoring is also possible if a corresponding consensus could be achieved. * Can such a change mean that the lock scope will be extended for both use cases (successful and failed function execution)?
* How much does this implementation matter for you?
* Would you like to achieve a small reduction of the object code there?
* How do you think about consequences from special communication settings by a well-known maintainer for my update suggestions?
Regards, Markus
| |