On Thu, 19 Oct 2017 14:04:43 +0200 SF Markus Elfring <elfr...@users.sourceforge.net> wrote:
> >> @@ -61,7 +61,7 @@ static struct iommu_table_group > >> *iommu_pseries_alloc_group(int node) table_group = > >> kzalloc_node(sizeof(*table_group), GFP_KERNEL, node); if > >> (!table_group) > >> - goto fail_exit; > >> + return NULL; > >> > >> tbl = kzalloc_node(sizeof(*tbl), GFP_KERNEL, node); > >> if (!tbl) > > > > I have seen quite a few fixes that do inverse of this patch after a > > piece of code allocating some extra piece of memory was added before > > code that just returns on fail because it is the first allocation in > > the function. > > > > This is not useful. > > How do you think about an information from the section “7) > Centralized exiting of functions” in the document “coding-style.rst” > then? > > “… > If there is no cleanup needed then just return directly. > …” There is also stated benefit " - errors by not updating individual exit points when making modifications are prevented " which is furthered by using the common cleanup even in case no cleanup is required but running the cleanup does not cause any harm. Thanks Michal
