Messages in this thread | | | Subject | Re: hwmon/sch5627: Use common error handling code in sch5627_probe() | From | SF Markus Elfring <> | Date | Tue, 13 Mar 2018 10:30:32 +0100 |
| |
> 1 file changed, 29 insertions(+), 31 deletions(-) > > So you are asking people to review 60 changed lines to save 2,
A bit of object code reduction might become useful also in this case.
> that alone should be the point where you stop yourself from > *even* sending this patch.
I proposed just another collateral evolution.
> Next time before you send a patch please carefully think if the > saving is worth the combination of reviewers time + the risk of > regressions (and keep in mind that both the reviewers time and > the risk of regressions cost increase for more complex changes).
Source code transformations were integrated in other software areas according to such a change pattern.
> As for this specific discussion, there are certain "design-patterns" > in the kernel, goto style error handling is one of them, the pattern > there ALWAYS is: … > Notice the fall-thoughs those are ALWAYS there, never, ever is > there a goto after a cleanup label.
It seems that I present an unusual update suggestion as a software design variant.
> Your patches black goto magic completely messes this up
You can view the proposal in such a way.
> and clearly falls under the CS101 rule: never use goto.
There might a target conflict with information from the section “7) Centralized exiting of functions” in the document “coding-style.rst”.
Regards, Markus
| |